Timezone: »
Over the last decade, deep networks have propelled machine learning to accomplish tasks previously considered far out of reach, human-level performance in image classification and game-playing. However, research has also shown that the deep networks are often brittle to distributional shifts in data: it has been shown that human-imperceptible changes can lead to absurd predictions. In many application areas, including physics, robotics, social sciences and life sciences, this motivates the need for robustness and interpretability, so that deep networks can be trusted in practical applications. Interpretable and robust models can be constructed by incorporating prior knowledge within the model or learning process as an inductive bias, thereby regularizing the model, avoiding overfitting, and making the model easier to understand for scientists who are non-machine-learning experts. Already in the last few years researchers from different fields have proposed various combinations of domain knowledge and machine learning and successfully applied these techniques to various applications.
Sat 6:30 a.m. - 6:35 a.m.
|
Introduction
(
Live
)
|
🔗 |
Sat 6:35 a.m. - 6:50 a.m.
|
Thomas Pierrot - Learning Compositional Neural Programs for Continuous Control
(
Contributed Talk
)
SlidesLive Video » |
Thomas PIERROT 🔗 |
Sat 6:50 a.m. - 7:10 a.m.
|
Jessica Hamrick - Structured Computation and Representation in Deep Reinforcement Learning
(
Invited Talk
)
SlidesLive Video » |
Jessica Hamrick 🔗 |
Sat 7:10 a.m. - 7:25 a.m.
|
Manu Kalia - Deep learning of normal form autoencoders for universal, parameter-dependent dynamics
(
Contributed Talk
)
SlidesLive Video » |
Manu Kalia 🔗 |
Sat 7:25 a.m. - 7:50 a.m.
|
Rose Yu - Physics-Guided AI for Learning Spatiotemporal Dynamics
(
Invited Talk
)
SlidesLive Video » |
Rose Yu 🔗 |
Sat 7:50 a.m. - 8:05 a.m.
|
Ferran Alet - Tailoring: encoding inductive biases by optimizing unsupervised objectives at prediction time
(
Contributed Talk
)
|
Ferran Alet 🔗 |
Sat 8:05 a.m. - 9:00 a.m.
|
Poster Session 1 ( Poster Session ) link » | 🔗 |
Sat 9:00 a.m. - 9:25 a.m.
|
Frank Noé - PauliNet: Deep Neural Network Solution of the Electronic Schrödinger Equation
(
Invited Talk
)
SlidesLive Video » |
Frank Noe 🔗 |
Sat 9:25 a.m. - 9:40 a.m.
|
Kimberly Stachenfeld - Graph Networks with Spectral Message Passing
(
Contributed Talk
)
SlidesLive Video » |
Kimberly Stachenfeld 🔗 |
Sat 9:40 a.m. - 10:10 a.m.
|
Franziska Meier - Inductive Biases for Models and Learning-to-Learn
(
Invited Talk
)
SlidesLive Video » |
Franziska Meier 🔗 |
Sat 10:10 a.m. - 10:25 a.m.
|
Rui Wang - Shapley Explanation Networks
(
Contributed Talk
)
SlidesLive Video » |
Rui Wang 🔗 |
Sat 10:25 a.m. - 10:55 a.m.
|
Jeanette Bohg - One the Role of Hierarchies for Learning Manipulation Skills
(
Invited Talk
)
SlidesLive Video » |
Jeannette Bohg 🔗 |
Sat 11:00 a.m. - 12:00 p.m.
|
Panel Discussion
|
🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
Poster Session 2 ( Posters ) link » | 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
1 - Real-time Classification from Short Event-Camera Streams using Input-filtering Neural ODEs
(
Poster
)
SlidesLive Video » |
Giorgio Giannone 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
2 - Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties
(
Poster
)
SlidesLive Video » |
Benjamin K Miller 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
3 - Improving the trustworthiness of image classification models by utilizing bounding-box annotations
(
Poster
)
|
Dharma R KC 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
4 - Physics-informed Generative Adversarial Networks for Sequence Generation with Limited Data
(
Poster
)
SlidesLive Video » |
Chacha Chen 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
5 - On the Structure of Cyclic Linear Disentangled Representations
(
Poster
)
SlidesLive Video » |
Matthew Painter 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
6 - Interpretable Models for Granger Causality Using Self-explaining Neural Networks
(
Poster
)
SlidesLive Video » |
Ričards Marcinkevičs 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
7 - A Symmetric and Object-Centric World Model for Stochastic Environments
(
Poster
)
|
Patrick Emami 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
8 - Individuality in the hive - Learning to embed lifetime social behavior of honey bees
(
Poster
)
SlidesLive Video » |
Benjamin Wild 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
9 - Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics
(
Poster
)
SlidesLive Video » |
Jiaxin Zhang 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
10 - A Trainable Optimal Transport Embedding for Feature Aggregation
(
Poster
)
SlidesLive Video » |
Grégoire Mialon 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
11 - A novel approach for semiconductor etching process with inductive biases
(
Poster
)
SlidesLive Video » |
Sanghoon Myung 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
12 - Physics-aware, data-driven discovery of slow and stable coarse-grained dynamics for high-dimensional multiscale systems
(
Poster
)
SlidesLive Video » |
Sebastian Kaltenbach 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
12 - IV-Posterior: Inverse Value Estimation forInterpretable Policy Certificates
(
Poster
)
SlidesLive Video » |
Tatiana López-Guevara 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
13 - Gradient-based Optimization for Multi-resource Spatial Coverage
(
Poster
)
SlidesLive Video » |
Nitin Kamra 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
14 - Learning Dynamical Systems Requires Rethinking Generalization
(
Poster
)
SlidesLive Video » |
Rui Wang 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
15 - Lie Algebra Convolutional Networks with Automatic Symmetry Extraction
(
Poster
)
SlidesLive Video » |
Nima Dehmamy 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
16 - An Image is Worth 16 × 16 Tokens: Visual Priors for Efficient Image Synthesis with Transformers
(
Poster
)
SlidesLive Video » |
Robin Rombach 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
17 - Uncovering How Neural Network Representations Vary with Width and Depth
(
Poster
)
SlidesLive Video » |
Thao Nguyen 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
18 - Simulating Surface Wave Dynamics with Convolutional Networks
(
Poster
)
SlidesLive Video » |
🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
19 - Choice of Representation Matters for Adversarial Robustness
(
Poster
)
SlidesLive Video » |
Amartya Sanyal 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
20 -SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency
(
Poster
)
SlidesLive Video » |
Sameer Dharur 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
21 - Solving Physics Puzzles by Reasoning about Paths
(
Poster
)
SlidesLive Video » |
Augustin Harter 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
22 - Modelling Advertising Awareness, an Interpretable and Differentiable Approach
(
Poster
)
SlidesLive Video » |
Luz Blaz 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
23 - Constraining neural networks output by an interpolating loss function with region priors
(
Poster
)
SlidesLive Video » |
Hannes Bergkvist 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
24 - Deep Context-Aware Novelty Detection
(
Poster
)
SlidesLive Video » |
Ellen Rushe 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
25 - Complex Skill Acquisition through Simple Skill Imitation Learning
(
Poster
)
|
Pranay Pasula 🔗 |
Sat 12:00 p.m. - 1:00 p.m.
|
26 - Is the Surrogate Model Interpretable?
(
Poster
)
SlidesLive Video » |
Sangwon Kim 🔗 |
Sat 1:00 p.m. - 1:15 p.m.
|
Liwei Chen - Deep Learning Surrogates for Computational Fluid Dynamics
(
Contributed Talk
)
SlidesLive Video » |
Nils Thuerey 🔗 |
Sat 1:15 p.m. - 2:15 p.m.
|
Maziar Raissi - Hidden Physics Models
(
Invited Talk
)
SlidesLive Video » |
Maziar Raissi 🔗 |
Sat 2:15 p.m. - 2:30 p.m.
|
Closing Remarks
(
Live
)
|
🔗 |
Author Information
Michael Lutter (TU Darmstadt)
Alexander Terenin (Imperial College London)
Shirley Ho (Flatiron institute/ New York University/ Carnegie Mellon)
Shirley Ho is a group leader and acting director at Flatiron Institute at Simons foundation, a research professor of physics and an affiliated faculty at Center for Data Science at NYU. Ho also holds associate (adjunct) professorship at Carnegie Mellon University and visiting appointment at Princeton University. She was a senior scientist at Berkeley National Lab from 2016-2018 and a Cooper-Siegel Development chair professor at Carnegie Mellon University before that. Ho was a Seaborg and Chamberlain Fellow from 2008-2011 at Berkeley Lab, after receiving her PhD in Astrophysics from Princeton University in 2008 under supervision of David Spergel. Ho graduated summa cum laude with a B.A. in Physics and a B.A. in Computer Science from UC Berkeley. A cited expert in cosmology, machine learning applications in astrophysics and data science,her interests are using deep learning accelerated simulations to understand the Universe, and other astrophysical phenomena. She tries her best to balance her love for the Universe, the machine and life especially during these crazy times.
Lei Wang (IOP, CAS)
More from the Same Authors
-
2021 : Searching for the Weirdest Stars: A Convolutional Autoencoder-Based Pipeline For Detecting Anomalous Periodic Variable Stars »
Ho-Sang Chan · Siu Hei Cheung · Victoria Villar · Shirley Ho -
2021 : A Convolutional Autoencoder-Based Pipeline For Anomaly Detection And Classification Of Periodic Variables »
Ho-Sang Chan · Siu Hei Cheung · Shirley Ho -
2021 : Equivariant and Modular DeepSets with Applications in Cluster Cosmology »
Leander Thiele · Miles Cranmer · Shirley Ho · David Spergel -
2021 : Sliced Multi-Marginal Optimal Transport »
Samuel Cohen · Alexander Terenin · Yannik Pitcan · Brandon Amos · Marc Deisenroth · Senanayak Sesh Kumar Karri -
2021 : Searching for the Weirdest Stars: A Convolutional Autoencoder-Based Pipeline For Detecting Anomalous Periodic Variable Stars »
Ho-Sang Chan · Siu Hei Cheung · Victoria Villar · Shirley Ho -
2022 : A Neural Network Subgrid Model of the Early Stages of Planet Formation »
Thomas Pfeil · Miles Cranmer · Shirley Ho · Philip Armitage · Tilman Birnstiel · Hubert Klahr -
2022 : Recovering Galaxy Cluster Convergence from Lensed CMB with Generative Adversarial Networks »
Liam Parker · Dongwon Han · Shirley Ho · Pablo Lemos -
2022 : Astronomical Image Coaddition with Bundle-Adjusting Radiance Fields »
Harlan Hutton · Harshitha Palegar · Shirley Ho · Miles Cranmer · Peter Melchior · Jenna Eubank -
2022 : Emulating cosmological growth functions with B-Splines »
Ngai Pok Kwan · Chirag Modi · Yin Li · Shirley Ho -
2022 : Adversarial Noise Injection for Learned Turbulence Simulations »
Jingtong Su · Julia Kempe · Drummond Fielding · Nikolaos Tsilivis · Miles Cranmer · Shirley Ho -
2022 : Learning Integrable Dynamics with Action-Angle Networks »
Ameya Daigavane · Arthur Kosmala · Miles Cranmer · Tess Smidt · Shirley Ho -
2021 : AI X Cosmology »
Shirley Ho -
2021 Poster: Vector-valued Gaussian Processes on Riemannian Manifolds via Gauge Independent Projected Kernels »
Michael Hutchinson · Alexander Terenin · Viacheslav Borovitskiy · So Takao · Yee Teh · Marc Deisenroth -
2021 : Coding Session 3 »
Shirley Ho · Miles Cranmer -
2021 : The Problem with Deep Learning for Physics (and how to fix it) »
Miles Cranmer · Shirley Ho -
2021 : Accelerating Simulations in Physics with Deep Learning »
Miles Cranmer · Shirley Ho -
2021 : Coding Session »
Shirley Ho · Miles Cranmer -
2021 : Physics-Informed Inductive Biases in Deep Learning »
Miles Cranmer · Shirley Ho -
2021 Tutorial: ML for Physics and Physics for ML »
Shirley Ho · Miles Cranmer -
2021 : The Intersection of ML and Physics »
Shirley Ho · Miles Cranmer -
2020 Workshop: Machine Learning and the Physical Sciences »
Anima Anandkumar · Kyle Cranmer · Shirley Ho · Mr. Prabhat · Lenka Zdeborová · Atilim Gunes Baydin · Juan Carrasquilla · Adji Bousso Dieng · Karthik Kashinath · Gilles Louppe · Brian Nord · Michela Paganini · Savannah Thais -
2020 Poster: Matérn Gaussian Processes on Riemannian Manifolds »
Viacheslav Borovitskiy · Alexander Terenin · Peter Mostowsky · Marc Deisenroth -
2020 Poster: Discovering Symbolic Models from Deep Learning with Inductive Biases »
Miles Cranmer · Alvaro Sanchez Gonzalez · Peter Battaglia · Rui Xu · Kyle Cranmer · David Spergel · Shirley Ho -
2019 : Opening Remarks »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2019 Workshop: Machine Learning and the Physical Sciences »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2017 : Poster Session »
Shunsuke Horii · Heejin Jeong · Tobias Schwedes · Qing He · Ben Calderhead · Ertunc Erdil · Jaan Altosaar · Patrick Muchmore · Rajiv Khanna · Ian Gemp · Pengfei Zhang · Yuan Zhou · Chris Cremer · Maria DeYoreo · Alexander Terenin · Brendan McVeigh · Rachit Singh · Yaodong Yang · Erik Bodin · Trefor Evans · Henry Chai · Shandian Zhe · Jeffrey Ling · Vincent ADAM · Lars Maaløe · Andrew Miller · Ari Pakman · Josip Djolonga · Hong Ge