Machine learning methods enable researchers to discover statistical patterns in large datasets to solve a wide variety of tasks, including in neuroscience. Recent advances have led to an explosion in the scope and complexity of problems to which machine learning can be applied, with an accuracy rivaling or surpassing that of humans in some domains.
This virtual conference will illuminate the many ways machine learning and neuroscience intersect in the context of data analysis and modeling brain function, and how neuroscience can benefit from the machine learning revolution.
- Basic machine learning concepts and resources.
- Machine learning methods to automate analyses of large neuroscience datasets.
- Using deep network learning to gain insight into how the brain learns.
- Combining machine learning concepts with neuroscience theory to predict nervous system function and uncover general principles.
The conference will end with speakers sharing their views on promising future directions for both machine learning and neuroscience.
SfN members, including Institutional Program members, are able to register for the virtual conference at the special member rate of $50, saving $100.
Not an SfN member? Nonmembers can register for the virtual conference at the registration rate of $150. Join SfN or renew your membership to register for the virtual conference at the special member rate of $50 (saving $100) and receive access to other SfN member benefits.
Receipt information is included in your registration confirmation email.Contact us if you have questions. Email firstname.lastname@example.org or call (202) 962-4000.
Click on each session title to reveal its description or download a one-page version of the agenda here.
Time: 11:00 a.m. – 11:45 a.m. EDT
The field of machine learning encompasses a broad range of data modeling and predictive tasks, and for each of these, a variety of approaches has been developed to address different application characteristics (e.g., different types of data). This session will provide a taxonomy of machine learning tasks and algorithms, illustrated by scientific applications.
Time: 12:00 p.m. – 1:00 p.m. EDT
Across neuroscience, from fMRI brain imaging of cognitive processing in humans to electron microscopy dissection of neuron connectivity in mice, scientists are producing datasets of unprecedented scale and complexity. Machine learning is a powerful tool for automating the processing and analysis of these datasets. In this session, Sebastian Seung and Leila Wehbe will discuss how machine learning is being used to analyze these types of data, and as a source of proposed models for the brain processes involved in the tasks behind the experiments. They will discuss different machine learning approaches and highlight pitfalls to avoid while pursuing them.
Time: 1:30 p.m. – 2:30 p.m. EDT
In addition to providing state-of-the-art tools for neural data analysis, machine learning methods can be useful to neuroscience as models of neural systems themselves. This session will focus on how machine learning principles provide an orienting normative perspective for making sense of brain data. Andrew Saxe and Kim Stachenfeld will show how understanding properties of learning in an artificial context can translate to insights about learning in the biological context, and discuss how machine learning problems and unexplained neuroscience data can mutually inform each other. Their talks will be augmented with examples from their work highlighting ML-neuro translational insights.
Time: 2:45 p.m. – 3:45 p.m. EDT
Unsupervised machine learning methods combine our prior hypotheses about the world with big data sets to discover new hypotheses. This session will describe the frontier of unsupervised machine learning algorithms and how they are being used to understand neuroscience data. Scott Linderman will present a short tutorial, “Finding Structure in Neural Data: From HMMs to Deep State Space Models,” which will cover both past and new ideas in state space modeling of neural data. Srini Turaga will present the use of variational autoencoders for Bayesian inference of spikes, synaptic inputs, and connectivity from calcium imaging and optogenetic perturbation experiments.
Time: 4:00 p.m. – 5:00 p.m. EDT
Panelists will share their views on the future of machine learning in neuroscience and answer questions from attendees.
Data Blitz Sessions
This virtual conference will include short data blitz videos accessible to attendees. These videos feature neuroscientists describing their research applying computer vision to neuroscience problems. The videos are available on demand, so you can watch them throughout the live day or after the conference.
Data blitz videos will be provided by:
- Beth Cimini, The Broad Institute
- Eyrún Eyjólfsdóttir, Vicarious
- Larissa Heinrich, HHMI Janelia Research Campus
- Talmo Pereira, Princeton University
Kristin Branson, PhD
Kristin Branson is a group leader and the head of computation and theory at the Howard Hughes Medical Institute's Janelia Research Campus. Her lab develops new machine vision and learning technologies to extract scientific understanding from large image data sets. Using these systems, Janelia Research Campus aims to gain insight into behavior and how it is generated by the nervous system. She earned her BA in computer science from Harvard University and her PhD in computer science from the University of California, San Diego, and completed postdoctoral training at the California Institute of Technology.
Beth Cimini, PhD
Beth Cimini is the lead image assay developer in the Carpenter Lab at the Broad Institute, collaborating with researchers around the world to build custom open-source image analysis workflows. She is also the co-maintainer of the lab's CellProfiler software. Always passionate about microscopy, she received her BA from Boston University while studying cholinergic signaling in the salamander retina, and her PhD in biochemistry and molecular biology from the University of California, San Francisco, studying telomere biology in cancer cells.
Sanjoy Dasgupta, PhD
Sanjoy Dasgupta is a professor of computer science and engineering at the University of California, San Diego, where he has been since 2002. Previously, he worked in the machine learning group at AT&T Labs Research. He obtained a BA from Harvard University in 1993 and a PhD from the University of California, Berkeley. Dasgupta works on algorithmic statistics, with a particular focus on unsupervised and minimally supervised learning. He is author (with Christos Papadimitriou and Umesh Vazirani) of a textbook, Algorithms. He was program co-chair of the Conference on Learning Theory in 2009 and of the International Conference on Machine Learning in 2013.
Eyrún Eyjólfsdóttir, PhD
Eyrún Eyjólfsdóttir is a research scientist at Vicarious, working on a computational vision system for robots. She completed her PhD at the California Institute of Technology, where she worked with Pietro Perona on automated analysis of behavior, particularly of fruit flies, in a collaboration with the David Anderson Lab. Prior to working at Caltech, she received her MS in computer science from the University of California, Santa Barbara, and her BS in mathematics from the University of Iceland.
Larissa Heinrich is a PhD student in the Saalfeld Lab at Janelia Research Campus, where she works on machine learning approaches for automated analysis of large electron microscopy datasets of neural tissue. She earned her BS and MS in physics at the University of Heidelberg, completing her thesis under Winfried Denk at the Max Planck Institute for Medical Research.
Scott Linderman, PhD
Scott Linderman is an assistant professor in the department of statistics and the Wu Tsai Neurosciences Institute at Stanford University. Prior to this, he was a postdoctoral fellow with Liam Paninski and David Blei at Columbia University. He completed his PhD in computer science at Harvard University with Ryan Adams and Leslie Valiant, and he received his BS in electrical and computer engineering from Cornell University. His research focuses on machine learning, computational neuroscience, and the general question of how computational and statistical methods can help us decipher neural computation.
Talmo Pereira is a PhD candidate in neuroscience at Princeton University. Advised by Mala Murthy and Joshua Shaevitz, Pereira has developed quantitative methods for studying animal behavior by employing a combination of computer vision and deep learning.
Andrew Saxe, PhD
Andrew Saxe is a postdoctoral research associate in the department of experimental psychology at the University of Oxford. He was previously a Swartz Postdoctoral Fellow in Theoretical Neuroscience at Harvard University. His research focuses on the theory of deep learning, applied to phenomena in neuroscience and psychology. He earned a BSE in electrical engineering from Princeton University and a PhD in electrical engineering from Stanford University.
Sebastian Seung, PhD
Sebastian Seung is Anthony B. Evnin Professor in the Neuroscience Institute and computer science department at Princeton University, and chief research scientist at Samsung Electronics. Seung has conducted influential research in computer science and neuroscience. He helped pioneer the new field of connectomics, applying deep learning and crowdsourcing to reconstruct neural circuits from electron microscopic images. His lab created EyeWire.org, a site that has recruited more than 250,000 players from 150 countries to map neural connections, and his book Connectome: How the Brain's Wiring Makes Us Who We Are was chosen by the The Wall Street Journal as one of the top ten nonfiction books of 2012. Before joining the Princeton faculty in 2014, Seung studied at Harvard University, worked at Bell Laboratories, and taught at the Massachusetts Institute of Technology. He is an external member of the Max Planck Society and the winner of the 2008 Ho-Am Prize in Engineering.
Kim Stachenfeld, PhD
Kimberly Stachenfeld is a research scientist on DeepMind’s neuroscience team. Her main focus is on representations to support efficient reinforcement learning and planning. She works on both neuroscience and machine learning problems in that space. Her research interests include the hippocampus and entorhinal cortex, reinforcement learning (deep and otherwise), efficient representations for reinforcement learning, and, on good days, fMRI.
Floh Thiels, PhD
Edda (Floh) Thiels is an adjunct associate professor of neurobiology at the University of Pittsburgh School of Medicine and a program director in the Directorate for Biological Sciences at the National Science Foundation. Thiels’ main research interests lie in how animals acquire information from the environment and use that information to guide their behavior. She received her undergraduate degree in psychology from the University of Toronto and her PhD in psychology from Indiana University.
Srini Turaga, PhD
Srini Turaga is a group leader at the Howard Hughes Medical Institute’s Janelia Research Campus, where his lab conducts research at the intersection of machine learning and neuroscience. He earned his PhD from the Massachusetts Institute of Technology under the supervision of Sebastian Seung. His postdoctoral fellowship at the Gatsby Unit at University College London was mentored jointly by Peter Dayan and Michael Häusser. His lab is currently researching machine learning for neural data analysis and modeling, connectomics, and computational microscopy.
Nicholas Turner is a PhD student in the Seung lab at Princeton University. His research focuses on neural circuit reconstruction of electron microscopy volumes and analysis of the resulting data. Specifically, he designed and implemented an automated system for synapse detection and assignment which has been applied to a petascale volume of mouse visual cortex. He earned a BA in psychology from Stanford University and an MA in Computer Science from Princeton University.
Leila Wehbe, PhD
Leila Wehbe is an assistant professor in the machine learning department at Carnegie Mellon University. Previously, she was a postdoctoral researcher in the Gallant Lab at the University of California, Berkeley. She obtained her PhD from the machine learning department and the Center for the Neural Basis of Cognition at Carnegie Mellon University, where she worked with Tom Mitchell. She studies language representations in the brain when subjects engage in naturalistic language tasks by combining functional neuroimaging with natural language processing and machine learning.