Workshops

When will a system that has performed well in the past continue to do so in the future? How do we design such systems in the presence of novel and potentially adversarial input distributions? What techniques will let us safely build and deploy autonomous systems on a scale where human monitoring becomes difficult or infeasible? Answering these questions is critical to guaranteeing the safety of emerging high stakes applications of AI, such as self-driving cars and automated surgical assistants. This workshop will bring together researchers in areas such as human-robot interaction, security, causal inference, and multi-agent systems in order to strengthen the field of reliability engineering for machine learning systems. We are interested in approaches that have the potential to provide assurances of reliability, especially as systems scale in autonomy and complexity. We will focus on four aspects — robustness (to adversaries, distributional shift, model mis-specification, corrupted data); awareness (of when a change has occurred, when the model might be mis-calibrated, etc.); adaptation (to new situations or objectives); and monitoring (allowing humans to meaningfully track the state of the system). Together, these will aid us in designing and deploying reliable machine learning systems.

Several applications necessitate learning a very large number of parameters from small amounts of data, which can lead to overfitting, statistically unreliable answers, and large training/prediction costs. A common and effective method to avoid the above mentioned issues is to restrict the parameter-space using specific structural constraints such as sparsity or low rank. However, such simple constraints do not fully exploit the richer structure which is available in several applications and is present in the form of correlations, side information or higher order structure. Designing new structural constraints requires close collaboration between domain experts and machine learning practitioners. Similarly, developing efficient and principled algorithms to learn with such constraints requires further collaborations between experts in diverse areas such as statistics, optimization, approximation algorithms etc. This interplay has given rise to a vibrant area of "learning with structure in high dimensions". The goal of this workshop is to bring together the aforementioned diverse set of people who have worked in these areas and encourage discussions with an aim to help define the current frontiers for the area and initiate a discussion about meaningful and challenging problems that require attention.

In adversarial training, a set of machines learn together by pursuing competing goals. For instance, in Generative Adversarial Networks (GANs, Goodfellow et al., 2014) a generator function learns to synthesize samples that best resemble some dataset, while a discriminator function learns to distinguish between samples drawn from the dataset and samples synthesized by the generator. GANs have emerged as a promising framework for unsupervised learning: GAN generators are able to produce images of unprecedented visual quality, while GAN discriminators learn features with rich semantics that lead to state-of-the-art semi-supervised learning (Radford et al., 2016). From a conceptual perspective, adversarial training is fascinating because it bypasses the need of loss functions in learning, and opens the door to new ways of regularizing (as well as fooling or attacking) learning machines. In this one-day workshop, we invite scientists and practitioners interested in adversarial training to gather, discuss, and establish new research collaborations. The workshop will feature invited talks, a hands-on demo, a panel discussion, and contributed spotlights and posters.

Among the research topics to be addressed by the workshop are

* Novel theoretical insights on adversarial training
* New methods and stability improvements for adversarial optimization
* Adversarial training as a proxy to unsupervised learning of representations
* Regularization and attack schemes based on adversarial perturbations
* Adversarial model evaluation
* Adversarial inference models
* Novel applications of adversarial training

Want to learn more? Get started by generating your own MNIST digits using a GAN in 100 lines of Torch: https://goo.gl/Z2leZF

The workshop focuses on the problem of privacy-preserving machine learning in scenarios where sensitive datasets are distributed across multiple data owners. Such distributed scenarios occur quite often in practice, for example when different parties contribute different records to a dataset, or information about each record in the dataset is held by different owners. Different communities have developed approaches to deal with this problem, including differential privacy-like techniques where noisy sketches are exchanged between the parties, homomorphic encryption where operations are performed on encrypted data, and tailored approaches using techniques from the field of secure multi-party computation. The workshop will serve as a forum to unify different perspectives on this problem and explore the relative merits of each approach. The workshop will also serve as a venue for networking researchers from the machine learning and secure multi-party computation communities interested in private learning, and foster fruitful long-term collaborations.

The workshop will have a particular emphasis in the decentralization aspect of privacy-preserving machine learning. This includes a large number of realistic scenarios where the classical setup of differential privacy with a "trusted curator" that prepares the data cannot be directly applied. The problem of privacy-preserving computation gains relevance in this model, and effectively leveraging the tools developed by the cryptographic community to develop private multi-party learning algorithms poses a remarkable challenge. Our program will include an introductory tutorial to secure multi-party computation for a machine learning audience, and talks by world-renowned experts from the machine learning and cryptography communities who have made high quality contributions to this problem.

We live in a multi-agent world and to be successful in that world, agents, and in particular, artificially intelligent agents, will need to learn to take into account the agency of others. They will need to compete in market places, cooperate in teams, communicate with others, coordinate their plans, and negotiate outcomes. Examples include self-driving cars interacting in traffic, personal assistants acting on behalf of humans and negotiating with other agents, swarms of unmanned aerial vehicles, financial trading systems, robotic teams, and household robots.

Furthermore, the evolution of human intelligence itself presumably depended on interaction among human agents, possibly starting out with confrontational scavenging [1] and culminating in the evolution of culture, societies, and language. Learning from other agents is a key feature of human intelligence and an important field of research in machine learning [2]. It is therefore conceivable that exposing learning AI agents to multi-agent situations is necessary for their development towards intelligence.

We can also think of multi-agent systems as a design philosophy for complex systems. We can analyse complex systems in terms of agents at multiple scales. For example, we can view the system of world politics as an interaction of nation state agents, nation states as an interaction of organizations, and further down into departments, people etc. Conversely, when designing systems we can think of agents as building blocks or modules interacting to produce the behaviour of the system, e.g. [3].

Multi-agent systems can have desirable properties such as robustness and scalability, but their design requires careful consideration of incentive structures, learning, and communication. In the most extreme case, agents with individual views of the world, individual actuators, and individual incentive structures need to coordinate to achieve a common goal. To succeed they may need a Theory of Mind that allows them to reason about other agents’ intentions, beliefs, and behaviours [4]. When multiple learning agents are interacting, the learning problem from each agent’s perspective may become non-stationary, non-Markovian, and only partially observable. Studying the dynamics of learning algorithms could lead to better insight about the evolution and stability of such systems [5].

Problems involving competing or cooperating agents feature in recent AI breakthroughs in competitive games [6,7], current ambitions of AI such as robotic football teams [8], and new research into emergent language and agent communication in reinforcement learning [9,10].

In summary, multi-agent learning will be of crucial importance to the future of computational intelligence and pose difficult and fascinating problems that need to be addressed across disciplines. The paradigm shift from single-agent to multi-agent systems will be pervasive and will require efforts across different fields including machine learning, cognitive science, robotics, natural computing, and (evolutionary) game theory. In this workshop we aim to bring together researchers from these different fields to discuss the current state of the art, future avenues and visions for work regarding theory and practice of multi-agent learning, inference, and decision-making.

Topics we consider for inclusion in the workshop include multi-agent reinforcement learning; deep multi-agent learning; theory of mind; multi-agent communication; POMDPs, Dec-POMDPS and partially observable stochastic games; multi-agent robotics, human-robot collaboration, swarm robotics; game theory, mechanism design, algorithms for computing nash equilibria and other solution concepts; bioinspired approaches, swarm intelligence and collective intelligence; co-evolution, evolutionary dynamics and culture; ad hoc teamwork.

[1] ‘Confrontational scavenging as a possible source for language and cooperation’, Derek Bickerton and Eörs Szathmáry, BMC Evolutionary Biology 2011
[2] ‘Apprenticeship Learning via Inverse Reinforcement Learning’, Pieter Abbeel and Andrew Y. Ng, ICML 2004
[3] ‘The Society of Mind’, Marvin Minsky, 1986
[4] ‘Building Machines That Learn and Think Like People’, Brenden M. Lake et al., CBMM Memo 2016
[5] ‘Evolutionary Dynamics of Multi-Agent Learning: A Survey’, Daan Bloembergen et al., JAIR 2015
[6] 'Mastering the game of Go with deep neural networks and tree search', David Silver et al., Nature 2016
[7] 'Heads-up limit hold’em poker is solved', Michael Bowling et al., Science 2015
[8] RoboCup, http://www.robocup.org/
[9] 'Learning to Communicate with Deep Multi-Agent Reinforcement Learning', Jakob N. Foerster et al., Arxiv 2016
[10] 'Learning Multiagent Communication with Backpropagation', Sainbayar Sukhbaatar et al. Arxiv 2016

The goal of this workshop is to bring together researchers from neuroscience, deep learning, machine learning, computer science theory, and statistics for a rich discussion about how computer science and neuroscience can inform one another as these two fields rapidly move forward. We invite high quality submissions and discussion on topics including, but not limited to, the following fundamental questions: a) shared approaches for analyzing biological and artificial neural systems, b) how insights and challenges from neuroscience can inspire progress in machine learning, and c) methods for interpreting the revolutionary large scale datasets produced by new experimental neuroscience techniques.

Experimental methods for measuring neural activity and structure have undergone recent revolutionary advances, including in high-density recording arrays, population calcium imaging, and large-scale reconstructions of anatomical circuitry. These developments promise unprecedented insights into the collective dynamics of neural populations and thereby the underpinnings of brain-like computation. However, these next-generation methods for measuring the brain’s architecture and function produce high-dimensional, large scale, and complex datasets, raising challenges for analysis. What are the machine learning and analysis approaches that will be indispensable for analyzing these next-generation datasets? What are the computational bottlenecks and challenges that must be overcome?

In parallel to experimental progress in neuroscience, the rise of deep learning methods has shown that hard computational problems can be solved by machine learning algorithms that are inspired by biological neural networks, and built by cascading many nonlinear units. In contrast to the brain, artificial neural systems are fully observable, so that experimental data-collection constraints are not relevant. Nevertheless, it has proven challenging to develop a theoretical understanding of how neural networks solve tasks, and what features are critical to their performance. Thus, while deep networks differ from biological neural networks in many ways, they provide an interesting testing ground for evaluating strategies for understanding neural processing systems. Are there synergies between analysis methods for biological and artificial neural systems? Has the resurgence of deep learning resulted in new hypotheses or strategies for trying to understand biological neural networks? Conversely, can neuroscience provide inspiration for the next generation of machine-learning algorithms?

We welcome participants from a range of disciplines in statistics, applied physics, machine learning, and both theoretical and experimental neuroscience, with the goal of fostering interdisciplinary insights. We hope that active discussions among these groups can set in motion new collaborations and facilitate future breakthroughs on fundamental research problems.

Deep Neural Networks have been revolutionizing several application domains in artificial intelligence: Computer Vision, Speech Recognition and Natural Language Processing. Concurrent to the recent progress in deep learning, significant progress has been happening in virtual reality, augmented reality, and smart wearable devices. These advances create unprecedented opportunities for researchers to tackle fundamental challenges in deploying deep learning systems to portable devices with limited resources (e.g. Memory, CPU, Energy, Bandwidth). Efficient methods in deep learning can have crucial impacts in using distributed systems, embedded devices, and FPGA for several AI tasks. Achieving these goals calls for ground-breaking innovations on many fronts: learning, optimization, computer architecture, data compression, indexing, and hardware design.

This workshop is sponsored by Allen Institute for Artificial Intelligence (AI2). We offer partial travel grant and registration for limited number of people participating in the workshop.

The goal of this workshop is providing a venue for researchers interested in developing efficient techniques for deep neural networks to present new work, exchange ideas, and build connections. The workshop will feature keynotes and invited talks from prominent researchers as well as a poster session that fosters in depth discussion. Further, in a discussion panel the experts discuss about the possible approaches (hardware, software, algorithm, ...) toward designing efficient methods in deep learning.

We invite submissions of short papers and extended abstracts related to the following topics in the context of efficient methods in deep learning:

-Network compression
-Quantized neural networks (e.g. Binary neural networks)
-Hardware accelerator for neural networks
-Training and inference with low-precision operations.
-Real-time applications in deep neural networks (e.g. Object detection, Image segmentation, Online language translation, ...)
-Distributed training/inference of deep neural networks
-Fast optimization methods for neural networks

Our transportation systems are poised for a transformation as we make progress on autonomous vehicles, vehicle-to-vehicle (V2V) and vehicle-to-everything (V2X) communication infrastructures, and smart road infrastructures such as smart traffic lights. There are many challenges in transforming our current transportation systems to the future vision. For example, how do we achieve near-zero fatality? How do we optimize efficiency through intelligent traffic management and control of fleets? How do we optimize for traffic capacity during rush hours? To meet these requirements in safety, efficiency, control, and capacity, the systems must be automated with intelligent decision making.

Machine learning will be essential to enable intelligent transportation systems. Machine learning has made rapid progress in self-driving, e.g. real-time perception and prediction of traffic scenes, and has started to be applied to ride-sharing platforms such as Uber (e.g. demand forecasting) and crowd-sourced video scene analysis companies such as Nexar (understanding and avoiding accidents). To address the challenges arising in our future transportation system such as traffic management and safety, we need to consider the transportation systems as a whole rather than solving problems in isolation. New machine learning solutions are needed as transportation places specific requirements such as extremely low tolerance on uncertainty and the need to intelligently coordinate self-driving cars through V2V and V2X.

The goal of this workshop is to bring together researchers and practitioners from all areas of intelligent transportations systems to address core challenges with machine learning. These challenges include, but are not limited to: predictive modeling of risk and accidents through telematics, modeling, simulation and forecast of demand and mobility patterns in large scale urban transportation systems, machine learning approaches for control and coordination of traffic leveraging V2V and V2X infrastructures, efficient pedestrian detection, pedestrian intent detection, intelligent decision-making for self-driving cars, scene classification, real-time perception and prediction of traffic scenes, deep reinforcement learning from human drivers, uncertainty propagation in deep neural networks, efficient inference with deep neural networks.

The workshop will include invited speakers, panels, presentations of accepted papers and posters. We invite papers in the form of short, long and position papers to address the core challenges mentioned above. We encourage researchers and practitioners on self-driving cars, transportation systems and ride-sharing platforms to participate.

Complex machine learning models, such as deep neural networks, have recently achieved great predictive successes for visual object recognition, speech perception, language modelling, and information retrieval. These predictive successes are enabled by automatically learning expressive features from the data. Typically, these learned features are a priori unknown, difficult to engineer by hand, and hard to interpret. This workshop is about interpreting the structure and predictions of these complex models.

Interpreting the learned features and the outputs of complex systems allows us to more fundamentally understand our data and predictions, and to build more effective models. For example, we may build a complex model to predict long range crime activity. But by interpreting the learned structure of the model, we can gain new insights into the processing driving crime events, enabling us to develop more effective public policy. Moreover, if we learn, for example, that the model is making good predictions by discovering how the geometry of clusters of crime events affect future activity, we can use this knowledge to design even more successful predictive models.

This 1 day workshop is focused on interpretable methods for machine learning, with an emphasis on the ability to learn structure which provides new fundamental insights into the data, in addition to accurate predictions. We will consider a wide range of topics, including deep learning, kernel methods, tensor methods, generalized additive models, rule based models, symbolic regression, visual analytics, and causality. A poster session, coffee breaks, and a panel guided discussion will encourage interaction between attendees. We wish to carefully review and enumerate modern approaches to the challenges of interpretability, share insights into the underlying properties of popular machine learning algorithms, and discuss future directions.

The prescriptive (normative) Bayesian theory of decision making under uncertainty has reached a high level of maturity. The assumption that the decision maker is rational (i.e. that they optimize expected utility, in Savage’s formulation) is central to this theory. However, empirical research indicates that this central assumption is often violated by real decision-makers. This limits the ability of the prescriptive Bayesian theory to provide a descriptive theory of the real world. One of the reasons that have been proposed for why the assumption of rationality might be violated by real decision makers is the limited cognitive and computational resources of those decision makers, [1]-[5]. This workshop intends to inspect this core assumption and to consider possible ways to modify or complement it.

Many of the precise issues related to this theme – some of which will be addressed in the invited talks - can be formulated as questions:

• Does the concept of rationality require Bayesian reasoning?
• Does quantum probability theory (extending classical Kolmogorov probability) provide novel insights into the relation between decision making and cognition?
• Do the extensions of expected utility (which is a linear function of the relevant probabilities) to nonlinear functions of probabilities enhance the flexibility of decision-making task formulating while respecting the limited cognitive resources of decision makers?
• How can good (meta-)heuristics, so successfully used by real-world decision makers, be elicited?

The list is definitely not complete and we expect that contributed talks, posters and informal discussions will extend it. To stimulate the informal discussions, the invited talks will be complemented by discussants challenging them. Altogether, the workshop aims to bring together diverse scientific communities, to brainstorm possible research directions, and to encourage collaboration among researchers with complementary ideas and expertise. The intended outcome is to understand and diminish the discrepancy between the established prescriptive theory and real-world decision making.

The targeted audience is scientists and students from the diverse scientific communities (decision science, cognitive science, natural science, artificial intelligence, machine learning, social science, economics, etc.) interested in various aspects of rationality.

All accepted submissions will be published in a special issue of the Workshop and Conference Proceedings series of the Journal of Machine Learning Research (JMRL).

[1] H.A. Simon: Theories Of Decision-Making In Economics and Behavioral Science, The American Economic Review, XLIX, 253-283, 1959
[2] C.A. Sims Implications of Rational Inattention, J. of Monetary Economics, 50, 3, 665 -- 690, 2003
[3] A. Tversky, D. Kahneman: Advances in Prospect Theory: Cumulative Representation of Uncertainty, J. of Risk and Uncertainty, 5, 297-323, 1992
[4] 2011 NIPS Workshop on Decision Making with Multiple Imperfect Decision Makers
[5] 2015 NIPS Workshop on Bounded Optimality and Metareasoning

Data, in the form of time-dependent sequential observations emerge in many key real-world problems, ranging from biological data, financial markets, weather forecasting to audio/video processing. However, despite the ubiquity of such data, most mainstream machine learning algorithms have been primarily developed for settings in which sample points are drawn i.i.d. from some (usually unknown) fixed distribution. While there exist algorithms designed to handle non-i.i.d. data, these typically assume specific parametric form for the data-generating distribution. Such assumptions may undermine the complex nature of modern data which can possess long-range dependency patterns, and for which we now have the computing power to discern. On the other extreme lie on-line learning algorithms that consider a more general framework without any distributional assumptions. However, by being purely-agnostic, common on-line algorithms may not fully exploit the stochastic aspect of time-series data.

Our workshop will build on the success of the first NIPS Time Series Workshop that was held at NIPS 2015. The goal of this workshop is to bring together theoretical and applied researchers interested in the analysis of time series and development of new algorithms to process sequential data. This includes algorithms for time series prediction, classification, clustering, anomaly and change point detection, correlation discovery, dimensionality reduction as well as a general theory for learning and comparing stochastic processes. We invite researchers from the related areas of batch and online learning, reinforcement learning, data analysis and statistics, econometrics, and many others to contribute to this workshop.

We also hope that this workshop will serve as an excellent companion to a tutorial on "Theory and Algorithms for Forecasting Non-Stationary Time Series" which is going to be presented at NIPS this year.

This year selected proceedings will be published in the JMLR special issue on "Time Series Analysis".

Adaptive data analysis is the increasingly common practice by which insights gathered from data are used to inform further analysis of the same data sets. This is common practice both in machine learning, and in scientific research, in which data-sets are shared and re-used across multiple studies. Unfortunately, most of the statistical inference theory used in empirical sciences to control false discovery rates, and in machine learning to avoid overfitting, assumes a fixed class of hypotheses to test, or family of functions to optimize over, selected independently of the data. If the set of analyses run is itself a function of the data, much of this theory becomes invalid, and indeed, has been blamed as one of the causes of the crisis of reproducibility in empirical science.

Recently, there have been several exciting proposals for how to avoid overfitting and guarantee statistical validity even in general adaptive data analysis settings. The problem is important, and ripe for further advances. The goal of this workshop is to bring together members of different communities (from machine learning, statistics, and theoretical computer science) interested in solving this problem, to share recent results, to discuss promising directions for future research, and to foster collaborations.

Recent years have seen the success of machine learning systems, in particular deep learning architectures, on specific challenges such as image classification and playing Go. Nevertheless, machines still fail on hallmarks of human intelligence such as the flexibility to quickly switch between a number of different tasks, the ability to creatively combine previously acquired skills in order to perform a more complex goal, the capacity to learn a new skill from just a few examples, or the use of communication and interaction to extend one's knowledge in order to accomplish new goals. This workshop aims to stimulate theoretical and practical advances in the development of machines endowed with human-like general-purpose intelligence, focusing in particular on benchmarks to train and evaluate progress in machine intelligence. The workshop will feature invited talks by top researchers from machine learning, AI, cognitive science and NLP, who will discuss with the audience their ideas about what are the most pressing issues we face in developing true AI and the best methods to measure genuine progress. We are moreover calling for position statements from interested researchers to complement the workshop program. The workshop will also introduce the new Environment for Communication-Based AI to the research community, encouraging discussion on how to make it the ultimate benchmark for machine intelligence. The Environment aims at being an interactive playground where systems can only succeed if they possess the hallmarks of intelligence we listed above. In September, we will make a prototype of the Environment available, so that researchers interested in submitting position statements to the workshop can experiment with it and take it into account in their proposals.

In theory, Bayesian nonparametric (BNP) methods are well suited to the large data sets that arise in the sciences, technology, politics, and other applied fields. By making use of infinite-dimensional mathematical structures, BNP methods allow the complexity of a learned model to grow as the size of a data set grows, exhibiting desirable Bayesian regularization properties for small data sets and allowing the practitioner to learn ever more from larger data sets. These properties have resulted in the adoption of BNP methods across a diverse set of application areas---including, but not limited to, biology, neuroscience, the humanities, social sciences, economics, and finance.

In practice, BNP methods present a number of computational and modeling challenges. Recent work has brought a wide range of models to bear on applied problems, going beyond the Dirichlet process and Gaussian process. Meanwhile, advances in accelerated inference are making these models tractable in big data problems.

In this workshop, we will explore new BNP methods for diverse applied problems, including cutting-edge models being developed by application domain experts. We will also discuss the limitations of existing methods and discuss key problems that need to be solved. A major focus of the workshop will be to expose participants to practical software tools for performing Bayesian nonparametric analyses. In particular, we plan to host hands-on tutorials to introduce workshop participants to some of the software packages that can be used to easily perform posterior inference for BNP models, e.g. Stan, BNPy, and BNP.jl.

We expect workshop participants to come from a variety of fields, including but not limited to machine learning, statistics, engineering, political science, and various biological sciences. The workshop will be relevant both to BNP experts as well as those interested in learning how to apply BNP models. There will be a special emphasis on work that makes BNP methods easy-to-use in practice and computationally efficient. Participants will leave the workshop with (i) exposure to recent advances in the field, (ii) hands-on experience with software implementing BNP methods, and (iii) an idea of the current challenges that need to be overcome in order to make BNP methods more widespread in practice. These goals will be accomplished through a series of invited and contributed talks, a poster session, and at least one hands-on tutorial session where participants can get their hands dirty with BNP methods.

This workshop builds off of the “Bayesian Nonparametrics: The Next Generation” workshop held at NIPS in 2015. While that workshop had a broad remit, spanning theory, applications and computation, this year’s workshop shows a fresh focus on the practical aspects of BNP methods. During last year’s panel discussion, there were many questions about computational techniques and practical applications, suggesting that this direction will be of great interest to the many applied machine learning researchers who attend the conference.

Deep learning is proven to be a powerful tool to build models for language (one-dimensional) and image (two-dimensional) understanding. Tremendous efforts have been devoted into these areas, however, it is still at the early stage to apply deep learning to 3D data, despite their great research values and broad real-world applications. In particular, existing methods poorly serve the three-dimensional data that drives a broad range of critical applications such as augmented reality, autonomous driving, graphics, robotics, medical imaging, neuroscience, and scientific simulations. These problems have drawn attention of researchers in different fields such as neuroscience, computer vision and graphics.

Different from text or images that can be naturally represented as 1D or 2D arrays, 3D data have multiple representation candidates, such as volumes, polygonal meshes, multi-views renderings, depth maps, and point clouds. Coupled with these representations are the myriad 3D learning problems, such as object recognition, scene layout estimation, compositional structure parsing, novel view synthesis, model completion and hallucination, etc. 3D data opens new and vast research space, which naturally calls for interdisciplinary expertise ranging from Computer Vision, Computer Graphics, to Machine Learning.

The goal of this workshop is to foster interdisciplinary communication of researchers working on 3D data (Computer Vision and Computer Graphics), so that more attention of broader community can be drawn to 3D deep learning problems. Through those studies, new ideas and discoveries are expected to emerge, which can inspire advances in related fields.

This workshop is composed of invited talks, oral presentations of outstanding submissions and a poster session to showcase the state-of-the-art results in the topic. In particular, a panel discussion among leading researchers in the field is planned, so as to provide a common playground for inspiring discussions and stimulating debates.

We aim to build a venue for publishing original research results in 3D deep learning, as well as exhibiting the latest trends and ideas. To be specific, we are interested in the following topics using 3D deep learning methods:

3D object detection from depth images and videos
3D scene understanding
3D spatial understanding from 2D images
3D shape classification and segmentation
3D mapping and reconstruction
Learning 3D geometrical properties and representations
Analysis of 3D medical and biological imaging data

We accept two tracks of submissions to the workshop on those topics: paper (6 - 9 pages) and extended abstract (4 pages). We are inviting researchers of related fields to join the workshop program committee to review the submissions. All the submissions will follow NIPS main conference paper style. The paper will be reviewed in double-blind form from three researchers in the workshop program committee. High quality papers will be selected for oral presentation. The abstracts will be reviewed by the workshop committee in single-blind fashion. Accepted submissions will either be presented as posters or talks at the workshop. We encourage submissions of works that has been previously published or is to be presented in the main conference.

Despite recent progress, AI is still far away from achieving common sense reasoning. One area that is gathering a lot of interest is that of intuitive or naive physics. It concerns the ability that humans and, to a certain extent, infants and animals have to predict outcomes of physical interactions involving macroscopic objects. There is extensive experimental evidence that infants can predict the outcome of events based on physical concepts such as gravity, solidity, object permanence and conservation of shape and number, at an early stage of development, although there is also evidence that this capacity develops through time and experience. Recent work has attempted to build neural models that can make predictions about stability, collisions, forces and velocities from images or videos, or interactions with an environment. Such models could be both used to understand the cognitive and neural underpinning of naive physics in humans, but also to provide with AI applications more better inference and reasoning abilities.

This workshop will bring together researchers in machine learning, computer vision, robotics, computational neuroscience, and cognitive development to discuss artificial systems that capture or model intuitive physics by learning from footage of, or interactions with a real or simulated environment. There will be invited talks from world leaders in the fields, presentations and poster sessions based on contributed papers, and a panel discussion.

Topics of discussion will include:
- Learning models of Newtonian physics (deep networks, structured probabilistic generative models, physics engines)
- How to combine model-based and bottom-up approaches to intuitive physics
- Application of intuitive physics models to higher-level tasks such as navigation, video prediction, robotics, etc.
- How cognitive science and computational neuroscience literature may inform the design of artificial systems for physical prediction
- Methodology for comparing models of infant learning with clinical studies
- Development of new datasets or platforms for intuitive physics and visual commonsense

Building systems that seamlessly integrate machine learning (ML) and human intelligence can greatly push the frontier of our ability to solve challenging real-world problems. While ML research usually focuses on developing more efficient learning algorithms, it is often the quality and amount of training data that predominantly govern the performance of real-world systems. This is only amplified by the recent popularity of large scale and complex learning methodologies such as Deep Learning, which can require millions to billions of training instances to perform well. The recent rise of human computation and crowdsourcing approaches, made popular by task-solving platforms like Amazon Mechanical Turk and CrowdFlower, enable us to systematically collect and organize human intelligence. Crowdsourcing research itself is interdisciplinary, combining economics, game theory, cognitive science, and human-computer interaction, to create robust and effective mechanisms and tools. The goal of this workshop is to bring crowdsourcing and ML experts together to explore how crowdsourcing can contribute to ML and vice versa. Specifically, we will focus on the design of mechanisms for data collection and ML competitions, and conversely, applications of ML to complex crowdsourcing platforms.

CROWDSOURCING FOR DATA COLLECTION

Crowdsourcing is one of the most popular approaches to data collection for ML, and therefore one of the biggest avenues through which crowdsourcing can advance the state of the art in ML. We seek cost-efficient and fast data collection methods based on crowdsourcing, and ask how design decisions in these methods could impact subsequent stages of ML system. Topics of interest include:
- Basic annotation: What is the best way to collect and aggregate labels for unlabeled data from the crowd? How can we increase fidelity by flagging labels as uncertain given the crowd feedback? How can we do the above in the most cost-efficient manner?
- Beyond simple annotation tasks: What is the most effective way to collect probabilistic data from the crowd? How can we collect data requiring global knowledge of the domain such as building Bayes net structure via crowdsourcing?
- Time-sensitive and complex tasks: How can we design crowdsourcing systems to handle real-time or time-sensitive tasks, or those requiring more complicated work dependencies? Can we encourage collaboration on complex tasks?
- Data collection for specific domains: How can ML researchers apply the crowdsourcing principles to specific domains (e.g., healthcare) where privacy and other concerns are at play?

ML RESEARCH VIA COMPETITIONS

Through the Netflix challenge and now platforms like Kaggle, we are seeing the crowdsourcing of ML research itself. Yet the mechanisms underlying these competitions are extremely simple. Here our focus is on the design of such competitions; topics of interest include:
- What is the most effective way to incentivize the crowd to participate in the ML competitions? What is the most efficient method; rather than the typically winner-takes-all, can we design a mechanism which makes better use of the net research-hours devoted to the competition?
- Competitions as recruiting: how would we design a competition differently if (as is often the case) the result is not a winning algorithm but instead a job offer?
- Privacy issues with data sharing are one of the key barriers to holding such competitions. How can we design privacy-aware mechanisms which allow enough access to enable a meaningful competition?
- Challenges arising from the sequential and interactive nature of competitions, e.g., how can we maintain unbiased leaderboards without allowing for overfitting?

ML FOR CROWDSOURCING SYSTEMS

General crowdsourcing systems such as Duolingo, FoldIt, and Galaxy Zoo confront challenges of reliability, efficiency, and scalability, for which ML can provide powerful solutions. Many ML approaches have already been applied to output aggregation, quality control, work flow management and incentive design, but there is much more that could be done, either through novel ML methods, major redesigns of workflow or mechanisms, or on new crowdsourcing problems. Topics here include:
- Dealing with sparse, noisy and large number of label classes, for example, in tagging image collection for Deep Learning based computer vision algorithms.
- Optimal budget allocation and active learning in crowdsourcing.
- Open theoretical questions in crowdsourcing that can be addressed by statistics and learning theory, for instance, analyzing label aggregation algorithms such as EM, or budget allocation strategies.
- Applications of ML to emerging crowd-powered marketplaces (e.g., Uber, AirBnb). How can ML improve the efficiency of these markets?

While early work on knowledge representation and inference was primarily symbolic, the corresponding approaches subsequently fell out of favor, and were largely supplanted by connectionist methods. In this workshop, we will work to close the gap between the two paradigms, and aim to formulate a new unified approach that is inspired by our current understanding of human cognitive processing. This is important to help improve our understanding of Neural Information Processing and build better Machine Learning systems, including the integration of learning and reasoning in dynamic knowledge-bases, and reuse of knowledge learned in one application domain in analogous domains.

The workshop brings together established leaders and promising young scientists in the fields of neural computation, logic and artificial intelligence, knowledge representation, natural language understanding, machine learning, cognitive science and computational neuroscience. Invited lectures by senior researchers will be complemented with presentations based on contributed papers reporting recent work (following an open call for papers) and a poster session, giving ample opportunity for participants to interact and discuss the complementary perspectives and emerging approaches.

The workshop targets a single broad theme of general interest to the vast majority of the NIPS community, namely translations between connectionist models and symbolic knowledge representation and reasoning for the purpose of achieving an effective integration of neural learning and cognitive reasoning, called neural-symbolic computing. The study of neural-symbolic computing is now an established topic of wider interest to NIPS with topics that are relevant to almost everyone studying neural information processing. In the 2016 edition of the workshop, special emphasis will be put on language-related aspects and applications of neural-symbolic integration and relevant cognitive computation paradigms.

Keywords: neural-symbolic computing; language processing and reasoning; cognitive agents; multimodal learning; deep networks; knowledge extraction; symbol manipulation; variable binding; memory-based networks; dynamic knowledge-bases.

This workshop explores the interface between cognitive neuroscience and recent advances in AI fields that aim to reproduce human performance such as natural language processing and computer vision, and specifically deep learning approaches to such problems.



When studying the cognitive capabilities of the brain, scientists follow a system identification approach in which they present different stimuli to the subjects and try to model the response that different brain areas have of that stimulus. The goal is to understand the brain by trying to find the function that expresses the activity of brain areas in terms of different properties of the stimulus. Experimental stimuli are becoming increasingly complex with more and more people being interested in studying real life phenomena such as the perception of natural images or natural sentences. There is therefore a need for a rich and adequate vector representation of the properties of the stimulus, that we can obtain using advances in NLP, computer vision or other relevant ML disciplines.



In parallel, new ML approaches, many of which in deep learning, are inspired to a certain extent by human behavior or biological principles. Neural networks for example were originally inspired by biological neurons. More recently, processes such as attention are being used which have are inspired by human behavior. However, the large bulk of these methods are independent of findings about brain function, and it is unclear whether it is at all beneficial for machine learning to try to emulate brain function in order to achieve the same tasks that the brain achieves.



In order to shed some light on this difficult but exciting question, we bring together many experts from these converging fields to discuss these questions, in a new highly interactive format focused on short lectures from experts in both fields, followed by a guided discussion. 



This workshop is a continuation of a successful workshop series: Machine Learning and Interpretation in Neuroimaging (MLINI). MLINI has already had 5 iterations in which methods for analyzing and interpreting neuroimaging data were discussed in depth. In keeping with previous tradition in the workshop, we also visit the blossoming field of machine learning applied to neuroimaging data, and specifically the recent trend of utilizing neural network models to analyze brain data, which is evolving on a seemingly orthogonal plane to the use of these algorithms to represent the information content in the brain. This way we will complete the loop of studying the advances of neural networks in neuroscience both as a source of models for brain representations, and as a tool for brain image analysis.

Challenges in machine learning and data science are competitions running over several weeks or months to resolve problems using provided datasets or simulated environments. The playful nature of challenges naturally attracts students, making challenge a great teaching resource. For this third edition of the CiML workshop at NIPS we want to explore more in depth the opportunities that challenges offer as teaching tools. The workshop will give a large part to discussions around several axes: (1) benefits and limitations of challenges to give students problem-solving skills and teach them best practices in machine learning; (2) challenges and continuous education and up-skilling in the enterprise; (3) design issues to make challenges more effective teaching aids; (4) curricula involving students in challenge design as a means of educating them about rigorous experimental design, reproducible research, and project leadership.
CiML is a forum that brings together workshop organizers, platform providers, and participants to discuss best practices in challenge organization and new methods and application opportunities to design high impact challenges. Following the success of last year's workshop (http://ciml.chalearn.org/), in which a fruitful exchange led to many innovations, we propose to reconvene and discuss new opportunities for challenges in education, one of the hottest topics identified in last year's discussions. We have invited prominent speakers in this field.
We will also reserve time to an open discussion to dig into other topic including open innovation, coopetitions, platform interoperability, and tool mutualisation.

Extreme classification, where one needs to deal with multi-class and multi-label problems involving a very large number of labels, has opened up a new research frontier in machine learning. Many challenging applications, such as photo or video annotation, web page categorization, gene function prediction, language modeling can benefit from being formulated as supervised learning tasks with millions, or even billions, of labels. Extreme classification can also give a fresh perspective on core learning problems such as ranking and recommendation by reformulating them as multi-class/label tasks where each item to be ranked or recommended is a separate label.

Extreme classification raises a number of interesting research questions including those related to:

* Large scale learning and distributed and parallel training
* Log-time and log-space prediction and prediction on a test-time budget
* Label embedding and tree-based approaches
* Crowd sourcing, preference elicitation and other data gathering techniques
* Bandits, semi-supervised learning and other approaches for dealing with training set biases and label noise
* Bandits with an extremely large number of arms
* Fine-grained classification
* Zero shot learning and extensible output spaces
* Tackling label polysemy, synonymy and correlations
* Structured output prediction and multi-task learning
* Learning from highly imbalanced data
* Dealing with tail labels and learning from very few data points per label
* PU learning and learning from missing and incorrect labels
* Feature extraction, feature sharing, lazy feature evaluation, etc.
* Performance evaluation
* Statistical analysis and generalization bounds
* Applications to ranking, recommendation, knowledge graph construction and other domains

The workshop aims to bring together researchers interested in these areas to encourage discussion and improve upon the state-of-the-art in extreme classification. In particular, we aim to bring together researchers from the natural language processing, computer vision and core machine learning communities to foster interaction and collaboration. Several leading researchers will present invited talks detailing the latest advances in the area. We also seek extended abstracts presenting work in progress which will be reviewed for acceptance as spotlight+poster or a talk. The workshop should be of interest to researchers in core supervised learning as well as application domains such as recommender systems, computer vision, computational advertising, information retrieval and natural language processing. We expect a healthy participation from both industry and academia.

http://www.manikvarma.org/events/XC16/schedule.html

A large body of machine learning problems require solving nonconvex optimization. This includes deep learning, Bayesian inference, clustering, and so on. The objective functions in all these instances are highly non-convex, and it is an open question if there are provable, polynomial time algorithms for these problems under realistic assumptions.

A diverse set of approaches have been devised to solve nonconvex problems in a variety of approaches. They range from simple local search approaches such as gradient descent and alternating minimization to more involved frameworks such as simulated annealing, continuation method, convex hierarchies, Bayesian optimization, branch and bound, and so on. Moreover, for solving special class of nonconvex problems there are efficient methods such as quasi convex optimization, star convex optimization, submodular optimization, and matrix/tensor decomposition.

There has been a burst of recent research activity in all these areas. This workshop brings researchers from these vastly different domains and hopes to create a dialogue among them. In addition to the theoretical frameworks, the workshop will also feature practitioners, especially in the area of deep learning who are developing new methodologies for training large scale neural networks. The result will be a cross fertilization of ideas from diverse areas and schools of thought.

Although the theory of reinforcement learning addresses an extremely general class of learning problems with a common mathematical formulation, its power has been limited by the need to develop task-specific feature representations. A paradigm shift is occurring as researchers figure out how to use deep neural networks as function approximators in reinforcement learning algorithms; this line of work has yielded remarkable empirical results in recent years. This workshop will bring together researchers working at the intersection of deep learning and reinforcement learning, and it will help researchers with expertise in one of these fields to learn about the other.

Bayesian analysis has seen a resurgence in machine learning, expanding its scope beyond traditional applications. Increasingly complex models have been trained with large and streaming data sets, and they have been applied to a diverse range of domains. Key to this resurgence has been advances in approximate Bayesian inference. Variational and Monte Carlo methods are currently the mainstay techniques, where recent insights have improved their approximation quality, provided black box strategies for fitting many models, and enabled scalable computation.

In this year's workshop, we would like to continue the theme of approximate Bayesian inference with additional emphases. In particular, we encourage submissions not only advancing approximate inference but also regarding (1) unconventional inference techniques, with the aim to bring together diverse communities; (2) software tools for both the applied and methodological researcher; and (3) challenges in applications, both in non-traditional domains and when applying these techniques to advance current domains.

The last decade has seen unprecedented growth in the availability and size of digital health data, including electronic health records, genetics, and wearable sensors. These rich data sources present opportunities to develop and apply machine learning methods to enable precision medicine. The aim of this workshop is to engender discussion between machine learning and clinical researchers about how statistical learning can enhance both the science and the practice of medicine.

Of particular interest to this year’s workshop is a phrase recently coined by the British Medical Journal, "Big Health Data", where the focus is on modeling and improving health outcomes across large numbers of patients with diverse genetic, phenotypic, and environmental characteristics. The majority of clinical informatics research has focused on narrow populations representing, for example, patients from a single institution or sharing a common disease, and on modeling clinical factors, such as lab test results and treatments. Big health considers large and diverse cohorts, often reaching over 100 million patients in size, as well as environmental factors that are known to impact health outcomes, including socioeconomic status, health care delivery and utilization, and pollution. Big Health Data problems pose a variety of challenges for standard statistical learning, many of them nontraditional. Including a patient’s race and income in statistical analysis, for example, evokes concerns about patient privacy. Novel approaches to differential privacy may help alleviate such concerns. Other examples include modeling biased measurements and non-random missingness and causal inference in the presence of latent confounders.

In this workshop we will bring together clinicians, health data experts, and machine learning researchers working on healthcare solutions. The goal is to have a discussion to understand clinical needs and the technical challenges resulting from those needs including the development of interpretable techniques which can adapt to noisy, dynamic environments and the handling of biases inherent in the data due to being generated during routine care.

Part of our workshop includes a clinician pitch, a five-minute presentation of open clinical problems that need data-driven solutions. These presentations will be followed by a discussion between invited clinicians and attending ML ­researchers to understand how machine learning can play a role in solving the problem presented. Finally, the pitch plays a secondary role of enabling new collaborations between machine learning researchers and clinicians: an important step for machine learning to have a meaningful role in healthcare. A general call for clinician pitches will be disseminated to clinical researchers and major physician organizations, including clinician social networks such as Doximity.

We will invite submission of two­ page abstracts (not including references) for poster contributions and short oral presentations describing innovative machine learning research on relevant clinical problems and data. Topics of interest include but are not limited to models for diseases and clinical data, temporal models, Markov decision processes for clinical decision support, multi­scale data-­integration, modeling with missing or biased data, learning with non-stationary data, uncertainty and uncertainty propagation, non ­i.i.d. structure in the data, critique of models, causality, model biases, transfer learning, and incorporation of non-clinical (e.g., socioeconomic) factors.

We are seeking sponsorship to help cover the travel and registration costs for students that are
presenting posters or short contributed talks, and for clinicians participating as speakers or presenting problem pitches. Workshop organizers have already discussed sponsorship with
the NSF, and also plan to approach industry leaders.

Interactive machine learning (IML) explores how intelligent agents solve a task together, often focusing on adaptable collaboration over the course of sequential decision making tasks. Past research in the field of IML has investigated how autonomous agents can learn to solve problems more effectively by making use of interactions with humans. Designing and engineering fully autonomous agents is a difficult and sometimes intractable challenge. As such, there is a compelling need for IML algorithms that enable artificial and human agents to collaborate and solve independent or shared goals. The range of real-world examples of IML spans from web applications such as search engines, recommendation systems and social media personalization, to dialog systems and embodied systems such as industrial robots and household robotic assistants, and to medical robotics (e.g. bionic limbs, assistive devices, and exoskeletons). As intelligent systems become more common in industry and in everyday life, the need for these systems to interact with and learn from the people around them will also increase.

This workshop seeks to brings together experts in the fields of IML, reinforcement learning (RL), human-computer interaction (HCI), robotics, cognitive psychology and the social sciences to share recent advances and explore the future of IML. Some questions of particular interest for this workshop include: How can recent advancements in machine learning allow interactive learning to be deployed in current real world applications? How do we address the challenging problem of seamless communication between autonomous agents and humans? How can we improve the ability to collaborate safely and successfully across a diverse set of users?

We hope that this workshop will produce several outcomes:
- A review of current algorithms and techniques for IML, and a focused perspective on what is lacking;
- A formalization of the main challenges for deploying modern interactive learning algorithms in the real world; and
- A forum for interdisciplinary researchers to discuss open problems and challenges, present new ideas on IML, and plan for future collaborations.

Topics relevant to this workshop include:
Human-robot interaction
Collaborative and/or shared control
Semi-supervised learning with human intervention
Learning from demonstration, interaction and/or observation
Reinforcement learning with human-in-the-loop
Active learning, Preference learning
Transfer learning (human-to-machine, machine-to-machine)
Natural language processing for dialog systems
Computer vision for human interaction with autonomous systems
Transparency and feedback in machine learning
Computational models of human teaching
Intelligent personal assistants and dialog systems
Adaptive user interfaces
Brain-computer interfaces (e.g. human-semi-autonomous system interfaces)
Intelligent medical robots (e.g. smart wheelchairs, prosthetics, exoskeletons)

The Royal Society is currently carrying out a major programme of work on machine learning, to assess its potential over the next 5-10 years, barriers to realising that potential, and the legal, ethical, social and scientific questions which arise as machine learning becomes more pervasive.
As part of this work, the Royal Society has carried out a public dialogue exercise to explore public awareness of, and attitudes towards, machine learning and its applications. The results of this work illustrate some of the key questions people have about machine learning; about why it is used, for what purpose, and with what pattern of benefits and disbenefits. It draws attention to the need to enable informed public debate that engages with specific applications.

In addition, machine learning is put to use in a range of different applications, it reframes existing social and ethical challenges, such as those relating to privacy and stereotyping, and also creates new challenges, such as interpretability, robustness and human-machine interaction. Many of these form the basis of active and stimulating areas of research, which can both move forward the field of machine learning and help address key governance issues.

The UK’s experience with other emerging technologies shows that it is possible to create arrangements that enable a robust public consensus on the safe and valuable use of even the most potentially contentious technologies. An effective dialogue process with the public can help to create these arrangements. From Twitter to Ted Talks, machine learning researchers have a range of ways in which they can engage with the public, and take an active role in public discussions about this technology. Yet, much of what the public hears about machine learning from the media focuses on accidents involving autonomous machines, or fears about labour market changes caused by direct substitution of people for machines.

This lunchtime session will present new research on the public’s view of machine learning, alongside a discussion of how research can help address some of the broader social challenges associated with machine learning.

Speakers: Dr Sabine Hauert speak about the Royal Society's recent public dialogues on machine learning and why it is important to engage with the public. Professor Zoubin Ghahramani will then explore the role of machine learning research in addressing areas of social concern, such as transparency and interpretability. Katherine Gorman will then discuss tools for communicating research to the public.

Lunch will be provided for attendees.

Workshop webpage: http://www.neurorobotic.eu

Modern robots are complex machines with many compliant actuators and various types of sensors including depth and vision cameras, tactile electrodes and dozens of proprioceptive sensors. The obvious challenges are to process these high dimensional input patterns, memorize low dimensional representations of them and to generate the desired motor commands to interact in dynamically changing environments. Similar challenges exist in brain machine interfaces (BMIs) where complex prostheses with perceptional feedback are controlled, or in motor neuroscience where in addition cognitive features need to be considered. Despite this broad research overlap the developments happened mainly in parallel and were not ported or exploited in the related domains. The main bottleneck for collaborative studies has been a lack of interaction between the core robotics, the machine learning and the neuroscience communities.

Why is it now just the right time for interactions?

- Latest developments based on deep neural networks have advanced the capabilities of robotic systems by learning control policies directly from the high dimensional sensor readings.
- Many variants of networks have been recently developed including the integration of feedback through recurrent connections, the projection to different feature spaces, may be trained at different time scales and can be modulated through additional inputs.
- These variants can be the basis for new models and concepts in motor neuroscience, where simple feed forward structures were not sufficiently powerful.
- Robotic applications demonstrated the feasibility of such networks for real time control of complex systems, which can be exploited in BMIs.
- Modern robots and new sensor technologies require models that can integrate a huge amount of inputs of different dimension, at different rates and with different noise levels. The neuroscience communities face such challenges and develop sophisticated models that can be evaluated in robotic applications used as benchmarks.
- New learning rules can be tested on real systems in challenging environments.


Topics:

- Convolutional Networks and Real-time Robotic and Prosthetic applications
- Deep Learning for Robotics and Prosthetics
- End-to-End Robotics / Learning
- Feature Representations for Big Data
- Movement Representations, Movement Primitives and Muscle Synergies
- Neural Network Hardware Implementation, Neuromorphic Hardware
- Recurrent Networks and Reservoirs for Control of high dimensional systems
- Reinforcement Learning and Bayesian Optimization in Neural Networks from multiple reward sources
- Sampling Methods and Spiking Networks for Robotics
- Theoretical Learning Concepts, Synaptic Plasticity Rules for Neural Networks

Real world data in many domains is multimodal and heterogeneous, such as healthcare, social media, and climate science. Tensors, as generalizations of vectors and matrices, provide a natural and scalable framework for handling data with inherent structures and complex dependencies. Recent renaissance of tensor methods in machine learning ranges from academic research on scalable algorithms for tensor operations, novel models through tensor representations, to industry solutions including Google TensorFlow and Tensor Processing Unit (TPU). In particular, scalable tensor methods have attracted considerable amount of attention, with successes in a series of learning tasks, such as learning latent variable models [Anandkumar et al., 2014; Huang et al., 2015, Ge et al., 2015], relational learning [Nickle et al., 2011, 2014, 2016], spatio-temporal forecasting [Yu et al., 2014, 2015, 2016] and training deep neural networks [Alexander et al., 2015].

These progresses trigger new directions and problems towards tensor methods in machine learning. The workshop aims to foster discussion, discovery, and dissemination of research activities and outcomes in this area and encourages breakthroughs. We will bring together researchers in theories and applications who are interested in tensors analysis and development of tensor-based algorithms. We will also invite researchers from related areas, such as numerical linear algebra, high-performance computing, deep learning, statistics, data analysis, and many others, to contribute to this workshop. We believe that this workshop can foster new directions, closer collaborations and novel applications. We also expect a deeper conversation regarding why learning with tensors at current stage is important, where it is useful, what tensor computation softwares and hardwares work well in practice and, how we can progress further with interesting research directions and open problems.

In recent years, we have seen a rise in the amount of education data available through the digitization of education. Schools are starting to use technology in classrooms to create personalized learning experiences. Massive open online courses (MOOCs) have attracted millions of learners and present an opportunity for us to apply and develop machine learning methods towards improving student learning outcomes, leveraging the data collected.

However, development in student data analysis remains limited, and education largely follows a one-size-fits-all approach today. We have an opportunity to have a significant impact in revolutionizing the way (human) learning can work.

The goal of this workshop is to foster discussion and spur research between machine learning experts and researchers in education fields that can solve fundamental problems in education.

For this year's workshop, we are highlighting the following areas of interest:

-- Assessments and grading
Assessments are core in adaptive learning, formative learning, and summative evaluation. However, the creation and grading of quality assessments remains a difficult task for instructors. Machine learning methods can be applied to self-, peer-, auto-grading paradigms to both improve the quality of assessments and reduce the burden on instructors and students. These methods can also leverage the multimodal nature of learner data (i.e., textual/programming/mathematical open-form responses, demographic information, student interaction in discussion forums, video and audio recording of the class), posing challenges of how to effectively and efficiently fuse these different forms of data so that we can better understand learners.

-- Content augmentation and understanding:
Learning content is rich and multimodal (e.g., programming code, video, text, audio). There has been a growth of online educational resources in the past years, and we have an opportunity to leverage them further. Recent advances in natural language understanding can be applied to understand learning materials better and connect different sources together to create better learning experiences. This can help learners by providing them with more relevant resources and instructors in the creation of content.

-- Personalized learning and active interventions:
Personalized learning through custom feedback and interventions can make learning much more efficient, especially when we cater to the individual's background, goals, state of understanding, and learning context. Methods such as Markov Decision Processes and Multi-armed Bandits are applicable in these context.

-- Human-interpretability:
In education applications, transparency and interpretability is important as it can help learners better understand their learning state. Interpretability can provide instructors with insights to better guide their activities with students. It can also help education researchers better understand the foundations of human learning. This can also be especially critical where models are deployed in processes that grade students, as evaluation needs to demonstrate a degree of fairness.

This workshop will lead to new research directions in machine learning-driven educational research and also inspire the development of novel machine learning algorithms and theories that can extend to a large number of other applications that study human data.

One of the promises of Big Data is its potential to answer “what if?” questions in digital, natural and social systems. Whether we speak of genetic interactions in a cell, passengers commuting in railways and roads, recommender systems matching users to ads, or understanding contagion in social networks, such systems are composed of many interacting components that suggest that learning to control them or understanding the effect of shocks to a system is not an easy task. What if some railways are closed, what will passengers do? What if we incentivize a member of a social network to propagate an idea, how influential can they be? What if some genes in a cell are knocked-out, which phenotypes can we expect?

Such questions need to be addressed via a combination of experimental and observational data, and require a careful approach to modelling heterogeneous datasets and structural assumptions concerning the causal relations among the components of the system. The workshop is aimed at bringing together research expertise from a variety of communities in machine learning, statistics, engineering, and the social, medical and natural sciences. It is an opportunity for methods for causal inference, reinforcement learning and game theory to be cross-fertilized with more traditional research in statistics and the real-world constraints found in practical applications. Ultimately, this can lead to new research platforms to aid the assessment of policies, shocks and experimental design methods in the discovery of breakthroughs in a variety of domains.

Workshop webpage: http://www.neurorobotic.eu

Modern robots are complex machines with many compliant actuators and various types of sensors including depth and vision cameras, tactile electrodes and dozens of proprioceptive sensors. The obvious challenges are to process these high dimensional input patterns, memorize low dimensional representations of them and to generate the desired motor commands to interact in dynamically changing environments. Similar challenges exist in brain machine interfaces (BMIs) where complex prostheses with perceptional feedback are controlled, or in motor neuroscience where in addition cognitive features need to be considered. Despite this broad research overlap the developments happened mainly in parallel and were not ported or exploited in the related domains. The main bottleneck for collaborative studies has been a lack of interaction between the core robotics, the machine learning and the neuroscience communities.

Why is it now just the right time for interactions?

- Latest developments based on deep neural networks have advanced the capabilities of robotic systems by learning control policies directly from the high dimensional sensor readings.
- Many variants of networks have been recently developed including the integration of feedback through recurrent connections, the projection to different feature spaces, may be trained at different time scales and can be modulated through additional inputs.
- These variants can be the basis for new models and concepts in motor neuroscience, where simple feed forward structures were not sufficiently powerful.
- Robotic applications demonstrated the feasibility of such networks for real time control of complex systems, which can be exploited in BMIs.
- Modern robots and new sensor technologies require models that can integrate a huge amount of inputs of different dimension, at different rates and with different noise levels. The neuroscience communities face such challenges and develop sophisticated models that can be evaluated in robotic applications used as benchmarks.
- New learning rules can be tested on real systems in challenging environments.


Topics:

- Convolutional Networks and Real-time Robotic and Prosthetic applications
- Deep Learning for Robotics and Prosthetics
- End-to-End Robotics / Learning
- Feature Representations for Big Data
- Movement Representations, Movement Primitives and Muscle Synergies
- Neural Network Hardware Implementation, Neuromorphic Hardware
- Recurrent Networks and Reservoirs for Control of high dimensional systems
- Reinforcement Learning and Bayesian Optimization in Neural Networks from multiple reward sources
- Sampling Methods and Spiking Networks for Robotics
- Theoretical Learning Concepts, Synaptic Plasticity Rules for Neural Networks

As the ninth in its series, OPT 2016 builds on remarkable precedent established by the highly successful series of workshops: OPT 2008--OPT 2015, which have been instrumental in bridging the OPT and ML communities closer together.

The previous OPT workshops enjoyed packed to overpacked attendance. This huge interest is no surprise: optimization is the 2nd largest topic at NIPS and is indeed foundational for the wider ML community.

Looking back over the past decade, a strong trend is apparent: The intersection of OPT and ML has grown monotonically to the point that now several cutting-edge advances in optimization arise from the ML community. The distinctive feature of optimization within ML is its departure from textbook approaches, in particular, by having a different set of goals driven by “big-data,” where both models and practical implementation are crucial.

This intimate relation between OPT and ML is the core theme of our workshop. We wish to use OPT2016 as a platform to foster discussion, discovery, and dissemination of the state-of-the-art in optimization as relevant to machine learning. And even beyond that, as a platform to identify new directions and challenges that will drive future research.

How OPT differs from other related workshops:

Compared to the other optimization focused workshops that we are aware of, the distinguishing features of OPT are: (a) it provides a unique bridge between the ML community and the wider optimization community; (b) it encourages theoretical work on an equal footing with practical efficiency; and (c) it caters to a wide body of NIPS attendees, experts and beginners alike (some OPT talks are always of a more “tutorial” nature).

Extended abstract

The OPT workshops have previously covered a variety of topics, such as frameworks for convex programs (D. Bertsekas), the intersection of ML and optimization, classification (S. Wright), stochastic gradient and its tradeoffs (L. Bottou, N. Srebro), structured sparsity (Vandenberghe), randomized methods for convex optimization (A. Nemirovski), complexity theory of convex optimization (Y. Nesterov), distributed optimization (S. Boyd), asynchronous stochastic gradient (B. Recht), algebraic techniques (P. Parrilo), nonconvex optimization (A. Lewis), sums-of-squares techniques (J. Lasserre), deep learning tricks (Y. Bengio), stochastic convex optimization (G. Lan), new views on interior point (E. Hazan), among others.

Several ideas propounded in OPT have by now become important research topics in ML and optimization --- especially in the field of randomized algorithms, stochastic gradient and variance reduced stochastic gradient methods. An edited book "Optimization for Machine Learning" (S. Sra, S. Nowozin, and S. Wright; MIT Press, 2011) grew out of the first three OPT workshops, and contains high-quality contributions from many of the speakers and attendees, and there have been sustained requests for the next edition of such a volume.

Much of the recent focus has been on large-scale first-order convex optimization algorithms for machine learning, both from a theoretical and methodological point of view. Covered topics included stochastic gradient algorithms, (accelerated) proximal algorithms, decomposition and coordinate descent algorithms, parallel and distributed optimization. Theoretical and practical advances in these methods remain a topic of core interest to the workshop. Recent years have also seen interesting advances in non-convex optimization such as a growing body of results on alternating minimization, tensor factorization etc.

We also do not wish to ignore the not particularly large scale setting, where one does have time to wield substantial computational resources. In this setting, high-accuracy solutions and deep understanding of the lessons contained in the data are needed. Examples valuable to MLers may be exploration of genetic and environmental data to identify risk factors for disease; or problems dealing with setups where the amount of observed data is not huge, but the mathematical model is complex. Consequently, we encourage optimization methods on manifolds, ML problems with differential geometric antecedents, those using advanced algebraic techniques, and computational topology, for instance.

At this point, we would like to emphasize again that OPT2016 is one of the few optimization+ML workshops that lies at the intersection of theory and practice: both actual efficiency of algorithms in practice as well as their theoretical analysis are given equal value.

The goal of this workshop is to bring together researchers from neuroscience, deep learning, machine learning, computer science theory, and statistics for a rich discussion about how computer science and neuroscience can inform one another as these two fields rapidly move forward. We invite high quality submissions and discussion on topics including, but not limited to, the following fundamental questions: a) shared approaches for analyzing biological and artificial neural systems, b) how insights and challenges from neuroscience can inspire progress in machine learning, and c) methods for interpreting the revolutionary large scale datasets produced by new experimental neuroscience techniques.

Experimental methods for measuring neural activity and structure have undergone recent revolutionary advances, including in high-density recording arrays, population calcium imaging, and large-scale reconstructions of anatomical circuitry. These developments promise unprecedented insights into the collective dynamics of neural populations and thereby the underpinnings of brain-like computation. However, these next-generation methods for measuring the brain’s architecture and function produce high-dimensional, large scale, and complex datasets, raising challenges for analysis. What are the machine learning and analysis approaches that will be indispensable for analyzing these next-generation datasets? What are the computational bottlenecks and challenges that must be overcome?

In parallel to experimental progress in neuroscience, the rise of deep learning methods has shown that hard computational problems can be solved by machine learning algorithms that are inspired by biological neural networks, and built by cascading many nonlinear units. In contrast to the brain, artificial neural systems are fully observable, so that experimental data-collection constraints are not relevant. Nevertheless, it has proven challenging to develop a theoretical understanding of how neural networks solve tasks, and what features are critical to their performance. Thus, while deep networks differ from biological neural networks in many ways, they provide an interesting testing ground for evaluating strategies for understanding neural processing systems. Are there synergies between analysis methods for biological and artificial neural systems? Has the resurgence of deep learning resulted in new hypotheses or strategies for trying to understand biological neural networks? Conversely, can neuroscience provide inspiration for the next generation of machine-learning algorithms?

We welcome participants from a range of disciplines in statistics, applied physics, machine learning, and both theoretical and experimental neuroscience, with the goal of fostering interdisciplinary insights. We hope that active discussions among these groups can set in motion new collaborations and facilitate future breakthroughs on fundamental research problems.

Machine learning methods have applied beyond their origins in artificial intelligence to a wide variety of data analysis problems in fields such as science, health care, technology, and commerce. Previous research in machine learning, perhaps motivated by its roots in AI, has primarily aimed at fully-automated approaches for prediction problems. But predictive analytics is only one step in the larger pipeline of data science, which includes data wrangling, data cleaning, exploratory visualization, data integration, model criticism and revision, and presentation of results to domain experts.


An emerging strand of work aims to address all of these challenges in one stroke is by automating a greater portion of the full data science pipeline. This workshop will bring together experts in machine learning, data mining, databases and statistics to discuss the challenges that arise in the full end-to-end process of collecting data, analysing data, and making decisions and building new methods that support, whether in an automated or semi-automated way, more of the full process of analysing real data.


Considering the full process of data science raises interesting questions for discussion, such as: What aspects of data analysis might potentially be automated and what aspects seem more difficult? Statistical model building often emphasizes interpretability and human understanding, while machine learning often emphasizes predictive modeling --- are ML methods truly suitable for supporting the full data analysis pipeline? Do recent advances in ML offer help here? Finally, are there low hanging fruit, i.e., how much time is wasted on routine tasks in scientific data analysis that could be automated?

Specific topics of interest include: data cleaning, exploratory data analysis, semi-supervised learning, active learning, interactive machine learning, model criticism, automated and semi-automated model construction, usable machine learning, interpretable prediction methods and automatic methods to explain predictions. We are especially interested in contributions that take a broader perspective, i.e., that aim toward supporting the process of data science more holistically.

A new area is emerging at the intersection of machine learning (ML) and systems design. This birth is driven by the explosive growth of diverse applications of ML in production, the continued growth in data volume, and the complexity of large-scale learning systems. Addressing the challenges in this intersection demands a combination of the right abstractions -- for algorithms, data structures, and interfaces -- as well as scalable systems capable of addressing real world learning problems.

Designing systems for machine learning presents new challenges and opportunities over the design of traditional data processing systems. For example, what is the right abstraction for data consistency in the context of parallel, stochastic learning algorithms? What guarantees of fault tolerance are needed during distributed learning? The statistical nature of machine learning offers an opportunity for more efficient systems but requires revisiting many of the challenges addressed by the systems and database communities over the past few decades. Machine learning focused developments in distributed learning platforms, programming languages, data structures, general purpose GPU programming, and a wide variety of other domains have had and will continue to have a large impact in both academia and industry.

As the relationship between the machine learning and systems communities has grown stronger, new research in using machine learning tools to solve classic systems challenges has also grown. Specifically, as we develop larger and more complex systems and networks for storing, analyzing, serving, and interacting with data, machine learning offers promise for modeling system dynamics, detecting issues, and making intelligent, data-driven decisions within our systems. Machine learning techniques have begun to play critical roles in scheduling, system tuning, and network analysis. Through working with systems and databases researchers to solve systems challenges, machine learning researchers can both improve their own learning systems as well impact the systems community and infrastructure at large.

The goal of this workshop is to bring together experts working at the crossroads of ML, system design and software engineering to explore the challenges faced when building practical large-scale machine learning systems. In particular, we aim to elicit new connections among these diverse fields, identify tools, best practices and design principles. The workshop will cover ML and AI platforms and algorithm toolkits (Caffe, Torch, TensorFlow, MXNet and parameter server, Theano, etc), as well as dive into the reality of applying ML and AI in industry with challenges of data and organization scale (with invited speakers from companies like Google, Microsoft, Facebook, Amazon, Netflix, Uber and Twitter).

The workshop will have a mix of invited speakers and reviewed papers with talks, posters and panel discussions to facilitate the flow of new ideas as well as best practices which can benefit those looking to implement large ML systems in academia or industry.

Focal points for discussions and solicited submissions include but are not limited to:
- Systems for online and batch learning algorithms
- Systems for out-of-core machine learning
- Implementation studies of large-scale distributed learning algorithms --- challenges faced and lessons learned
- Database systems for Big Learning --- models and algorithms implemented, properties (fault tolerance, consistency, scalability, etc.), strengths and limitations
- Programming languages for machine learning
- Data driven systems --- learning for job scheduling, configuration tuning, straggler mitigation, network configuration, and security
- Systems for interactive machine learning
- Systems for serving machine learning models at scale

Humans conversing naturally with machines is a staple of science fiction. Building agents capable of mutually coordinating their states and actions via communication, in conjunction with human agents, would be one of the Average engineering feats of human history. In addition to the tremendous economic potential of this technology, the ability to converse appears intimately related to the overall goal of AI.

Although dialogue has been an active area within the linguistics and NLP communities for decades, the wave of optimism in the machine learning community has inspired increased interest from researchers, companies, and foundations. The NLP community has enthusiastically embraced and innovated neural information processing systems, resulting in substantial relevant activity published outside of NIPS. A forum for increased interaction (dialogue!) with these communities at NIPS will accelerate creativity and progress.

We plan to focus on the following issues:

1. How to be data-driven
a. What are tractable and useful intermediate tasks on the path to truly conversant machines? How can we leverage existing benchmark tasks and competitions? What design criteria would we like to see for the next set of benchmark tasks and competitions?
b. How do we assess performance? What can and cannot be done with offline evaluation on fixed data sets? How can we facilitate development of these offline evaluation tasks in the public domain? What is the role of online evaluation as a benchmark, and how would we make it accessible to the general community? Is there a role for simulated environments, or tasks where machines communicate solely with each other?
2. How to build applications
a. What unexpected problem aspects arise in situated systems? human-hybrid systems? systems learning from adversarial inputs?
b. Can we divide and conquer? Do we need to a irreducible end-to-end system, or can we define modules with abstractions that do not leak?
c. How do we ease the burden on the human designer of specifying or bootstrapping the system?
3. Architectural and algorithmic innovation
a. What are the associated requisite capabilities for learning architectures, and where are the deficiencies in our current architectures? How can we leverage recent advances in reasoning, attention, and memory architectures? How can we beneficially incorporate linguistic knowledge into our architectures?
b. How far can we get with current optimization techniques? To learn requisite competencies, do we need advances in discrete optimization? curriculum learning? (inverse) reinforcement learning?

The calculation of gradients and other forms of derivatives is a core part of machine learning, computer vision, and physical simulation. But the manual creation of derivatives is prone to error and requires a high "mental overhead" for practitioners in these fields. However, the process of taking derivatives is actually the highly mechanical application of the chain rule and can be computed using formal techniques such as automatic or symbolic differentiation. A family of "autodiff" approaches exist, each with their own particular strengths and tradeoffs.

In the ideal case, automatically generated derivatives should be competitive with manually generated ones and run at near-peak performance on modern hardware, but the most expressive systems for autodiff which can handle arbitrary, Turing-complete programs, are unsuited for performance-critical applications, such as large-scale machine learning or physical simulation. Alternatively, the most performant systems are not designed for use outside of their designated application space, e.g. graphics or neural networks. This workshop will bring together developers and researchers of state-of-the-art solutions to generating derivatives automatically and discuss ways in which these solutions can be evolved to be both more expressive and achieve higher performance. Topics for discussion will include:

- Whether it is feasible to create a single differentiable programming language, or if we will always have separate solutions for different fields such as vision and ML.
- What are the primitive data types of a differentiable language? N-dimensional arrays are useful for many machine learning applications, but other domains make use of graph types and sparse matrices.
- What are the challenges in elevating an expressive autodiff implementation from just a “prototyping language” to one used directly in performance-critical industrial settings?
- A shared representation of programs like LLVM IR has transformed programming language and compiler research. Is there any benefit to a common representation of differentiable programs that would enable shared tooling amongst autodiff libraries and implementations?

A crucial, high impact application of learning systems is forecasting. While machine learning has already been applied to time series analysis and signal processing, the recent big data revolution allows processing and prediction of vast data flows and forecasting of high dimensional, spatiotemporal series using massive multi-modal streams as predictors. Wider data bandwidths allow machine learning techniques such as connectionist and deep learning methods to assist traditional forecasting methods from fields such as engineering and econometrics, while probabilistic methods are uniquely suited to address the stochastic nature of many processes requiring forecasting.

This workshop will bring together multi-disciplinary researchers from signal processing, statistics, machine learning, computer vision, economics and causality looking to widen their application or methodological scope. It will begin by providing a forum to discuss pressing application areas o forecasting: video compression and understanding, energy and and smart grid management, economics and finance, environmental and health policy (e.g. epidemiology), as well as introduce challenging new datasets. A large dataset, created for an industry-driven data competition, will be presented - this dataset not only helps develop and compare new methods for forecasting, but also addresses deeper underlying learning theory questions: do effective learning systems truly infer underlying structure or merely output accuracy in data streams?, is transfer learning available at no loss to specificity? and is semi-supervised learning is an inherent property of powerful, accurate, learning machines? What strategies are scalable so they perform well on sparse as well as big data? What exactly is a good forecasting machine? Therefore a forum is also planned to discuss such pressing issues,- dedicated poster sessions and panels are scheduled. We plan for a varied list of reknowned speakers, presenting data sources, rich open-source platforms for forecasting, prediction performance evaluation metrics, past forecasting competitions and state-of-the-art methods.

Computer Vision is a mature field with long history of academic research, but recent advances in deep learning provided machine learning models with new capabilities to understand visual content. There have been tremendous improvements on problems like classification, detection, segmentation, which are basic proxies for the ability of a model to understand the visual content. These are accompanied by a steep rise of Computer Vision adoption in industry at scale, and by more complex tasks such as Image Captioning and Visual Q&A. These go well beyond the classical problems and open the doors to a whole new world of possibilities. As industrial applications mature, the challenges slowly shift towards challenges in data, in scale, and in moving from purely visual data to multi-modal data.

The unprecedented adoption of Computer Vision to numerous real world applications processing billions of "live" media content daily, raises a new set of challenges, including:

1. Efficient Data Collection (Smart sampling, weak annotations, ...)
2. Evaluating performance in the wild (long tails, embarrassing mistakes, calibration)
3. Incremental learning: Evolve systems incrementally in complex environments (new data, new categories, federated architectures ...)
4. Handling tradeoffs: Computation vs Accuracy vs Supervision
5. Outputs are various types (Binary predictions, embeddings etc.)
6. Machine learning feedback loops
7. Minimizing technical debt as system matures
8. On-device vs On-cloud vs Split
9. Multi-modal content understanding

We will bring together researchers and practitioners who are interested to address this new set of challenges and provide a venue to share how industry and academia approach these problems. We will invite prominent speakers from academia and industry to give their perspectives on these challenges. In addition, we will have 5 minute spotlights for selected papers submitted to the workshop and a poster session for all selected submissions. The topics of submissions should be related to the above mentioned list of challenges. We will end the session with a panel discussion including the speakers on the future of large scale vision and its applications in the wild.

In the second part we will looke at how specifically this applies to video understanding. Video understanding aims at developing computer methods that can interpret videos at different semantic levels. Applications include video categorization, event detection, semantic segmentation, description, summarization, tagging, content-­based retrieval, surveillance, and many more. Although in the last two decades the field of video analytics has witnessed significant progress, most problems in this area still remain largely unsolved. In recent years video understanding has become an even more critical and timely problem to address because of the tremendous growth of videos on the Internet, most of which do not contain tags or descriptions and thus necessitate automatic analysis to become searchable or browsable. At the same time the rise of online video repositories represents an opportunity for the creation of new pivotal large­-scale datasets for research in this area. Given the recent breakthroughs achieved by deep learning in other big data domains, we believe that video understanding may very well be on the verge of a technical revolution that will spur significant advances in this area.

In order to foster further progress by the research community, we propose to organize a one-­day workshop to discuss emerging innovations and ideas about the problems and challenges related to video understanding. The workshop will consist of a series of invited talks from researchers in this area. In addition, we will publicly announce and present a new large­-scale benchmark for video comprehension [1] that has the potential to become an instrumental resource for future research in this field. Compared to existing video datasets, our proposed benchmark has much bigger scale and it casts video understanding in the novel form of multiple choice tests that assess the ability of the algorithm to comprehend the semantics of the video.

This workshop will be the first of a series of annual meetings that we will organize to stimulate steady progress in this area. In each subsequent edition of this workshop, we will host an annual challenge on our continuously expanding video comprehension benchmark in order to motivate students and researchers to push the envelope on this problem. We hope to bring together researchers with common interests in video analysis to share, learn, and make good progress toward better video understanding methods.

[1] D. Tran, M. Paluri, and L. Torresani, “ViCom: Benchmark and Methods for Video Comprehension,” CoRR, abs/1606.07373, July 2016,
http://arxiv.org/abs/1606.07373

Deep learning systems that act in and interact with an environment must reason about how actions will change the world around them. The natural regime for such real-world decision problems involves supervision that is weak, delayed, or entirely absent, and the outputs are typically in the context of sequential decision processes, where each decision affects the next input. This regime poses a challenge for deep learning algorithms, which typically excel with: (1) large amounts of strongly supervised data and (2) a stationary distribution of independently observed inputs. The algorithmic tools for tackling these challenges have traditionally come from reinforcement learning, optimal control, and planning, and indeed the intersection of reinforcement learning and deep learning is currently an exciting and active research area. At the same time, deep learning methods for interactive decision-making domains have also been proposed in computer vision, robotics, and natural language processing, often using different tools and algorithmic formalisms from classical reinforcement learning, such as direct supervised learning, imitation learning, and model-based control. The aim of this workshop will be to bring together researchers across these disparate fields. The workshop program will focus on both the algorithmic and theoretical foundations of decision making and interaction with deep learning, and the practical challenges associated with bringing to bear deep learning methods in interactive settings, such as robotics, autonomous vehicles, and interactive agents.

The field of computational biology has seen dramatic growth over the past few years. A wide range of high-throughput technologies developed in the last decade now enable us to measure parts of a biological system at various resolutions—at the genome, epigenome, transcriptome, and proteome levels. These technologies are now being used to collect data for an ever-increasingly diverse set of problems, ranging from classical problems such as predicting differentially regulated genes between time points and predicting subcellular localization of RNA and proteins, to models that explore complex mechanistic hypotheses bridging the gap between genetics and disease, population genetics and transcriptional regulation. Fully realizing the scientific and clinical potential of these data requires developing novel supervised and unsupervised learning methods that are scalable, can accommodate heterogeneity, are robust to systematic noise and confounding factors, and provide mechanistic insights.

The goals of this workshop are to i) present emerging problems and innovative machine learning techniques in computational biology, and ii) generate discussion on how to best model the intricacies of biological data and synthesize and interpret results in light of the current work in the field. We will invite several leaders at the intersection of computational biology and machine learning who will present current research problems in computational biology and lead these discussions based on their own research and experiences. We will also have the usual rigorous screening of contributed talks on novel learning approaches in computational biology. We encourage contributions describing either progress on new bioinformatics problems or work on established problems using methods that are substantially different from established alternatives. Deep learning, kernel methods, graphical models, feature selection, non-parametric models and other techniques applied to relevant bioinformatics problems would all be appropriate for the workshop. We will also encourage contributions to address new challenges in analyzing data generated from gene editing, single cell genomics and other novel technologies. The targeted audience are people with interest in machine learning and applications to relevant problems from the life sciences, including NIPS participants without any existing research link to computational biology. Many of the talks will be of interest to the broad machine learning community.

The "wiring diagram" of essentially all nervous systems remains unknown due to the extreme difficulty of measuring detailed patterns of synaptic connectivity of entire neural circuits. At this point, the major bottleneck is in the analysis of tera or peta-voxel 3d electron microscopy image data in which neuronal processes need to be traced and synapses localized in order for connectivity information to be inferred. This presents an opportunity for machine learning and machine perception to have a fundamental impact on advances in neurobiology. However, it also presents a major challenge, as existing machine learning methods fall short of solving the problem.
The goal of this workshop is to bring together researchers in machine learning and neuroscience to discuss progress and remaining challenges in this exciting and rapidly growing field. We aim to attract machine learning and computer vision specialists interested in learning about a new problem, as well as computational neuroscientists at NIPS who may be interested in modeling connectivity data. We will discuss the release of public datasets and competitions that may facilitate further activity in this area. We expect the workshop to result in a significant increase in the scope of ideas and people engaged in this field.

Despite remarkable computational success, artificial neural networks ignore the spiking nature of neural communication that is fundamental for biological neuronal networks. Understanding how spiking neurons process information and learn remains an essential challenge. It concerns not only neuroscientists studying brain function, but also neuromorphic engineers developing low-power computing architectures, or machine learning researchers devising new biologically-inspired learning algorithms. Unfortunately, despite a joint interest in spike-based computation, the interactions between these subfields remains limited. The workshop aims to bring them together and to foster the exchange between them by focusing on recent developments in efficient neural coding and spiking neurons' computation. The discussion will center around critical questions in the field, such as "what are the underlying paradigms?" "what are the fundamental constraints?", and "what are the measures for progress?”, that benefit from varied perspectives. The workshop will combine invited talks reviewing the state-of-the-art and short contributed presentations; it will conclude with a panel discussion.

http://www.probabilistic-numerics.org/meetings/NIPS2016/

Optimization problems in machine learning have aspects that make them more challenging than the traditional settings, like stochasticity, and parameters with side-effects (e.g., the batch size and structure). The field has invented many different approaches to deal with these demands. Unfortunately - and intriguingly - this extra functionality seems to invariably necessitate the introduction of tuning parameters: step sizes, decay rates, cycle lengths, batch sampling distributions, and so on. Such parameters are not present, or at least not as prominent, in classic optimization methods. But getting them right is frequently crucial, and necessitates inconvenient human “babysitting”.

Recent work has increasingly tried to eliminate such fiddle factors, typically by statistical estimation. This also includes automatic selection of external parameters like the batch-size or -structure, which have not traditionally been treated as part of the optimization task. Several different strategies have now been proposed, but they are not always compatible with each other, and lack a common framework that would foster both conceptual and algorithmic interoperability. This workshop aims to provide a forum for the nascent community studying automating parameter-tuning in optimization routines.

Among the questions to be addressed by the workshop are:

* Is the prominence of tuning parameters a fundamental feature of stochastic optimization problems? Why do classic optimization methods manage to do well with virtually no free parameters?
* In which precise sense can the "optimization of optimization algorithms" be phrased as an inference / learning problem?
* Should, and can, parameters be inferred at design-time (by a human), at compile-time (by an external compiler with access to a meta-description of the problem) or run-time (by the algorithm itself)?
* What are generic ways to learn parameters of algorithms, and inherent difficulties for doing so? Is the goal to specialize to a particular problem, or to generalize over many problems?

In addition to the invited and already confirmed speakers, we will also invite contributed work from the community. Topics of interest include, but are not strictly limited to,

* Parameter adaptation for optimization algorithms
* Stochastic optimization methods
* Optimization methods adapted for specific applications
* Batch selection methods
* Convergence diagnostics for optimization algorithms

Bayesian optimization has emerged as an exciting subfield of machine learning that is concerned with the global optimization of expensive, noisy, black-box functions using probabilistic methods. Systems implementing Bayesian optimization techniques have been successfully used to solve difficult problems in a diverse set of applications. Many recent advances in the methodologies and theory underlying Bayesian optimization have extended the framework to new applications and provided greater insights into the behaviour of these algorithms. Bayesian optimization is now increasingly being used in industrial settings, providing new and interesting challenges that require new algorithms and theoretical insights.
Classically, Bayesian optimization has been used purely for expensive single-objective black-box optimization. However, with the increased complexity of tasks and applications, this paradigm is proving to be too restricted. Hence, this year’s theme for the workshop will be “black-box optimization and beyond”. Among the recent trends that push beyond BO we can briefly enumerate:
- Adapting BO to not-so-expensive evaluations.
- “Open the black-box” and move away from viewing the model as a way of simply fitting a response surface, and towards modelling for the purpose of discovering and understanding the underlying process. For instance, this so-called grey-box modelling approach could be valuable in robotic applications for optimizing the controller, while simultaneously providing insight into the mechanical properties of the robotic system.
- “Meta-learning”, where a higher level of learning is used on top of BO in order to control the optimization process and make it more efficient. Examples of such meta-learning include learning curve prediction, Freeze-thaw Bayesian optimization, online batch selection, multi-task and multi-fidelity learning.
- Multi-objective optimization where not a single objective, but multiple conflicting objectives are considered (e.g., prediction accuracy vs training time).
The target audience for this workshop consists of both industrial and academic practitioners of Bayesian optimization as well as researchers working on theoretical and practical advances in probabilistic optimization. We expect that this pairing of theoretical and applied knowledge will lead to an interesting exchange of ideas and stimulate an open discussion about the long term goals and challenges of the Bayesian optimization community.
A further goal is to encourage collaboration between the diverse set of researchers involved in Bayesian optimization. This includes not only interchange between industrial and academic researchers, but also between the many different subfields of machine learning which make use of Bayesian optimization or its components. We are also reaching out to the wider optimization and engineering communities for involvement.

Humans have the extraordinary ability to learn continually from experience. Not only can we apply previously learned knowledge and skills to new situations, we can also use these as the foundation for later learning. One of the grand goals of AI is building an artificial "continual learning" agent that constructs a sophisticated understanding of the world from its own experience, through the autonomous incremental development of ever more complex skills and knowledge.

Hallmarks of continual learning include: interactive, incremental, online learning (learning occurs at every moment, with no fixed tasks or data sets); hierarchy or compositionality (previous learning can become the foundation far later learning); "isolaminar" construction (the same algorithm is used at all stages of learning); resistance to catastrophic forgetting (new learning does not destroy old learning); and unlimited temporal abstraction (both knowledge and skills may refer to or span arbitrary periods of time).

Continual learning is an unsolved problem which presents particular difficulties for the deep-architecture approach that is currently the favored workhorse for many applications. Some strides have been made recently, and many diverse research groups have continual learning on their road map. Hence we believe this is an opportune moment for a workshop focusing on this theme. The goals would be to define the different facets of the continual-learning problem, to tease out the relationships between different relevant fields (such as reinforcement learning, deep learning, lifelong learning, transfer learning, developmental learning, computational neuroscience, etc.) and to propose and explore promising new research directions.

Large amounts of high-dimensional data are routinely acquired in scientific fields ranging from biology, genomics and health sciences to astronomy and economics due to improvements in engineering and data acquisition techniques. Nonparametric methods allow for better modelling of complex systems underlying data generating processes compared to traditionally used linear and parametric models. From statistical point of view, scientists have enough data to reliably fit nonparametric models. However, from computational point of view, nonparametric methods often do not scale well to big data problems.

The aim of this workshop is to bring together practitioners, who are interested in developing and applying nonparametric methods in their domains, and theoreticians, who are interested in providing sound methodology. We hope to effectively communicate advances in development of computational tools for fitting nonparametric models and discuss challenging future directions that prevent applications of nonparametric methods to big data problems.

We encourage submissions on a variety of topics, including but not limited to:
- Randomized procedures for fitting nonparametric models. For example, sketching, random projections, core set selection, etc.
- Nonparametric probabilistic graphical models
- Scalable nonparametric methods
- Multiple kernel learning
- Random feature expansion
- Novel applications of nonparametric methods
- Bayesian nonparametric methods
- Nonparametric network models

This workshop is a fourth in a series of NIPS workshops on modern nonparametric methods in machine learning. Previous workshops focused on time/accuracy tradeoffs, high dimensionality and dimension reduction strategies, and automating the learning pipeline.

While deep learning has been revolutionary for machine learning, most modern deep learning models cannot represent their uncertainty nor take advantage of the well studied tools of probability theory. This has started to change following recent developments of tools and techniques combining Bayesian approaches with deep learning. The intersection of the two fields has received great interest from the community over the past few years, with the introduction of new deep learning models that take advantage of Bayesian techniques, as well as Bayesian models that incorporate deep learning elements.

In fact, the use of Bayesian techniques in deep learning can be traced back to the 1990s', in seminal works by Radford Neal, David MacKay, and Dayan et al.. These gave us tools to reason about deep models confidence, and achieved state-of-the-art performance on many tasks. However earlier tools did not adapt when new needs arose (such as scalability to big data), and were consequently forgotten. Such ideas are now being revisited in light of new advances in the field, yielding many exciting new results.

This workshop will study the advantages and disadvantages of such ideas, and will be a platform to host the recent flourish of ideas using Bayesian approaches in deep learning and using deep learning tools in Bayesian modelling. The program will include a mix of invited talks, contributed talks, and contributed posters. Also, the historic context of key developments in the field will be explained in an invited talk, followed by a tribute talk to David MacKay's work in the field. Future directions for the field will be debated in a panel discussion.

In many real-world applications, machine learning algorithms are employed as a tool in a ''constructive process''. These processes are similar to the general knowledge-discovery process but have a more specific goal: the construction of one-or-more domain elements with particular properties. In this workshop we want to bring together domain experts employing machine learning tools in constructive processes and machine learners investigating novel approaches or theories concerning constructive processes as a whole. Interesting applications include but are not limited to: image synthesis, drug and protein design, computational cooking, generation of art (paintings, music, poetry). Interesting approaches include but are not limited to: deep generative learning, active approaches to structured output learning, transfer or multi-task learning of generative models, active search or online optimization over relational domains, and learning with constraints.

Many of the applications of constructive machine learning, including the ones mentioned above, are primarily considered in their respective application domain research area but are hardly present at machine learning conferences. By bringing together domain experts and machine learners working on constructive ML, we hope to bridge this gap between the communities.

Machine intelligence capable of learning complex procedural behavior, inducing (latent) programs, and reasoning with these programs is a key to solving artificial intelligence. The problems of learning procedural behavior and program induction have been studied from different perspectives in many computer science fields such as program synthesis, probabilistic programming, inductive logic programming, reinforcement learning, and recently in deep learning. However, despite the common goal, there seems to be little communication and collaboration between the different fields focused on this problem.

Recently, there have been a lot of success stories in the deep learning community related to learning neural networks capable of using trainable memory abstractions. This has led to the development of neural networks with differentiable data structures such as Neural Turing Machines, Memory Networks, Neural Stacks, and Hierarchical Attentive Memory, among others. Simultaneously, neural program induction models like Neural Program Interpreters and Neural Programmer have created a lot of excitement in the field, promising induction of algorithmic behavior, and enabling inclusion of programming languages in the processes of execution and induction, while staying end-to-end trainable. Trainable program induction models have the potential to make a substantial impact in many problems involving long-term memory, reasoning, and procedural execution, such as question answering, dialog, and robotics.

The aim of the NAMPI workshop is to bring researchers and practitioners from both academia and industry, in the areas of deep learning, program synthesis, probabilistic programming, inductive programming and reinforcement learning, together to exchange ideas on the future of program induction with a special focus on neural network models and abstract machines. Through this workshop we look to identify common challenges, exchange ideas among and lessons learned from the different fields, as well as establish a (set of) standard evaluation benchmark(s) for approaches that learn with abstraction and/or reason with induced programs.

Areas of interest for discussion and submissions include, but are not limited to (in alphabetical order):
- Applications
- Compositionality in Representation Learning
- Differentiable Memory
- Differentiable Data Structures
- Function and (sub-)Program Compositionality
- Inductive Logic Programming
- Knowledge Representation in Neural Abstract Structures
- Large-scale Program Induction
- Meta-Learning and Self-improving
- Neural Abstract Machines
- Program Induction: Datasets, Tasks, and Evaluation
- Program Synthesis
- Probabilistic Programming
- Reinforcement Learning for Program Induction
- Semantic Parsing

This workshop focuses on recent advances to end-to-end methods for speech and more general audio processing. Deep learning has transformed the state of the art in speech recognition, and audio analysis in general. In recent developments, new deep learning architectures have made it possible to integrate the entire inference process into an end-to-end system. This involves solving problems of an algorithmic nature, such as search over time alignments between different domains, and dynamic tracking of changing input conditions. Topics include automatic speech recognition systems (ASR) and other audio procssing systems that subsume front-end adaptive microphone array processing and source separation as well as back-end constructs such as phonetic context dependency, dynamic time alignment, or phoneme to grapheme modeling. Other end-to-end audio applications include speaker diarization, source separation, and music transcription. A variety of architectures have been proposed for such systems, ranging from shift-invariant convolutional pooling to connectionist temporal classification (CTC) and attention based mechanisms, or other novel dynamic components. However there has been little comparison yet in the literature of the relative merits of the different approaches. This workshop delves into questions about how different approaches handle various trade-offs in terms of modularity and integration, in terms of representation and generalization. This is an exciting new area and we expect significant interest from the machine learning and speech and audio processing communities.