Discovering Dynamics in Massive-scale Neural Datasets Using Machine Learning

Chethan Pandarinath, Department of Biomedical Engineering
Emory University

Matthew T. Kaufman, Department of Organismal Biology and Anatomy
University of Chicago

People: Fabio Rizzoglio, Xuan Ma, Ege Altan, Kevin Bodkin

In the fifty years since Ed Evarts first recorded single neurons in M1 of behaving monkeys, great effort has been devoted to understanding the relation between these individual signals and movement-related signals collected during highly constrained motor behaviors performed by over-trained monkeys. In parallel, theoreticians posited that the computations performed in the brain depend critically on network-level phenomena: dynamical laws in brain circuits that constrain the activity and dictate how it evolves over time. We can now record from hundreds of neurons simultaneously but are still at an early stage in developing tools for determining how networks of neurons work together to perceive the world and to generate the control signals needed to produce coordinated movement. The goal of this project, directed by Dr. Chethan Pandarinath at Emory University, is to develop a powerful new suite of tools, based on deep learning, to analyze the dynamics of neural datasets at unprecedented temporal and spatial scales. Because deep learning thrives on big data, we can leverage massive-scale brain recordings. In the Miller lab, this will include week-long recordings of the activity of 100 neurons as a monkey goes about its daily business. In Dr. Matt Kauffman’s lab at the University of Chicago, this means recording from thousands of neurons with two-photon imaging for hours in the mouse, each identified with an exact location in the brain and tied to the mouse's on-going behaviors. Novel machine learning techniques from Chethan’s group using sequential auto-encoders will enable the investigators to learn the dynamics underlying these data. This combination will provide windows into the brain's control of motor behavior that have never before been possible. The novel analytical framework developed here will be extensible from motor behaviors to higher level problems of error processing, decision making, and learning. These approaches will open new windows on how neurons act together moment-by-moment to produce movement.