Timezone: »

Brains and Bits: Neuroscience meets Machine Learning
Alyson Fletcher · Eva Dyer · Jascha Sohl-Dickstein · Joshua T Vogelstein · Konrad Koerding · Jakob H Macke

Thu Dec 08 11:00 PM -- 09:30 AM (PST) @ Room 211
Event URL: http://www.stat.ucla.edu/~akfletcher/brainsbits.html »

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.

Thu 11:30 p.m. - 11:45 p.m.
Welcome and Opening Remarks (Talk)
Allie Fletcher, Konrad P Koerding
Thu 11:45 p.m. - 12:30 a.m.
Christos Papadimitriou : A computer scientist thinks about the brain (Keynote) Christos Papadimitriou
Fri 12:30 a.m. - 1:00 a.m.
Cristina Savin : Spike-Based Probabilistic Computation (Talk)
Cristina Savin
Fri 1:00 a.m. - 1:30 a.m.
Mitya Chklovskii : Toward Biologically Plausible Machine Learning: A Similarity Matching Approach (Talk)
Dmitri B Chklovskii
Fri 1:30 a.m. - 2:00 a.m.
Coffee Break 1a (plus posters) (Break)
Fri 2:00 a.m. - 2:30 a.m.
Jonathan Pillow : Scalable Inference for Structured Hierarchical Receptive Field Models (Talk) Jonathan W Pillow
Fri 2:30 a.m. - 3:00 a.m.
Emily Fox : Functional Connectivity in MEG via Graphical Models of Time Series (Talk) Emily Fox
Fri 3:00 a.m. - 3:30 a.m.
Srini Turaga : Independence testing & Amortized inference, with neural networks, for neuroscience (Talk)
Srini C Turaga
Fri 3:30 a.m. - 5:00 a.m.
Lunch Day 1 (Lunch)
Fri 5:00 a.m. - 5:30 a.m.
Il Memming Park : Dynamical Systems Interpretation of Neural Trajectories (Talk) Memming Park
Fri 5:30 a.m. - 6:00 a.m.
David Sussillo : LFADS - Latent Factor Analysis via Dynamical Systems (Talk)
David Sussillo
Fri 6:00 a.m. - 6:30 a.m.
Coffee Break 1b (plus posters) (Break)
Fri 6:30 a.m. - 7:00 a.m.
Poster Session 1 (Poster Session)
Fri 7:00 a.m. - 7:30 a.m.
Eva Dyer (Talk)
Eva Dyer
Fri 7:30 a.m. - 8:00 a.m.
Michael Buice (Talk)
Fri 8:00 a.m. - 8:30 a.m.
Stefan Mihalas : Modeling Optimal Context Integration in Cortical Columns (Talk)
Stefan Mihalas
Fri 8:30 a.m. - 9:00 a.m.
Breakout Discussion Afternoon Session (Breakout Discussion)
Konrad P Koerding
Fri 11:30 p.m. - 11:45 p.m.
Opening Remarks (Talk)
Jascha Sohl-Dickstein
Fri 11:45 p.m. - 12:30 a.m.
Yoshua Bengio : Toward Biologically Plausible Deep Learning (Keynote)
Yoshua Bengio
Sat 12:30 a.m. - 1:00 a.m.
Surya Ganguli : Deep Neural Models of the Retinal Response to Natural Stimuli (Talk)
Surya Ganguli
Sat 1:00 a.m. - 1:30 a.m.
Max Welling : Making Deep Learning Efficient Through Sparsification (Talk)
Max Welling
Sat 1:30 a.m. - 2:00 a.m.
Coffee Break 2a (plus posters) (Break)
Sat 2:00 a.m. - 2:30 a.m.
David Cox : Predictive Coding for Unsupervised Feature Learning (Talk)
David Cox
Sat 2:30 a.m. - 3:30 a.m.
From Brains to Bits and Back Again (Discussion Panel)
Yoshua Bengio, Terrence Sejnowski, Christos H Papadimitriou, Jakob H Macke, Demis Hassabis, Allie Fletcher, Andreas Tolias, Jascha Sohl-Dickstein, Konrad P Koerding
Sat 3:30 a.m. - 5:00 a.m.
Lunch Day 2 (Break)
Sat 5:00 a.m. - 5:30 a.m.
Fred Hamprecht : Motif Discovery in Functional Brain Data (Talk)
Fred Hamprecht
Sat 5:30 a.m. - 6:00 a.m.
Anima Anandkumar (Talk)
Anima Anandkumar
Sat 6:00 a.m. - 6:30 a.m.
Coffee Break 2b (plus posters) (Break)
Sat 6:30 a.m. - 7:00 a.m.
Poster Session 2 (Poster Session)
Sat 7:00 a.m. - 7:30 a.m.
Kanitscheider : Training Recurrent Networks to Generate Hypotheses About How the Brain Solves Hard Navigation Problems (Talk)
Ingmar Kanitscheider
Sat 7:30 a.m. - 8:00 a.m.
Jorg Lucke : Probabilistic Inference and the Brain: Towards General, Scalable, and Deep Approximations (Talk)
Jörg Lücke

Author Information

Allie Fletcher (UCLA)
Eva Dyer (Georgia Institute of Technology)

Eva Dyer is an Assistant Professor in the Wallace H. Coulter Department of Biomedical Engineering at the Georgia Institute of Technology and Emory University. Dr. Dyer completed her M.S. and Ph.D degrees in Electrical & Computer Engineering at Rice University in 2011 and 2014, respectively. Eva's research interests lie at the intersection of data science, machine learning, and neuroscience.

Jascha Sohl-Dickstein (Google Brain)
Joshua T Vogelstein (The Johns Hopkins University)
Konrad Koerding
Jakob H Macke (research center caesar, an associate of the Max Planck Society)

More from the Same Authors