University of Pittsburgh

Department of Neurobiology

Presents a Special Seminar:

“Using machine learning to predict how genetic variation will influence the brain”

Dr. Andreas R. Pfenning
Assistant Professor, Computational Biology and Neuroscience Institute
Carnegie Mellon University

Wednesday
May 18^th, 2022
1 pm

https://pitt.zoom.us/j/91800136889

To join us, register by Tuesday, May 17. You will receive a Zoom login link in a confirmation email. Follow this link to register. 

If you have any questions, contact CMUevents@andrew.cmu.edu.

About the Event

To understand the brain, neuroscientists need the best possible tools.

From brain-computer interfaces to non-invasive neuroimaging techniques, Carnegie Mellon is changing the field of neuroscience. These technological advances are deepening our understanding of the brain and even improving our ability to diagnose and treat brain injuries and disorders.

Join Barbara Shinn-Cunningham, director of CMU’s Neuroscience Institute, and other faculty experts for an exploration of their groundbreaking neuro technology and engineering research and the implications for the future of neuroscience.

Featuring

Carnegie Mellon University programs and events are open to all alumni, regardless of race, color, national origin, sex, handicap or disability, age, sexual orientation, gender identity, religion, creed, ancestry, belief, veteran status or genetic information.

Carsen Stringer (Janelia) will be visiting Friday, 05/20.
She will be giving a seminar at 10am, in BST S100. Hope to see you all there.

“Making sense of large-scale neural and behavioral data”

Large-scale neural recordings contain high-dimensional structure that cannot be easily captured by existing data visualization methods. We therefore developed an embedding algorithm called Rastermap, which captures complex temporal and highly nonlinear relationships between neurons, and provides useful visualizations by assigning each neuron to a location in the embedding space. We applied Rastermap to a variety of datasets, including spontaneous neural activity, neural activity during a virtual reality task, widefield neural imaging data from a 2AFC task, and artificial neural activity from an agent playing atari games. We found within these datasets unique subpopulations of neurons encoding abstract elements of decision-making, the environment and behavioral states. To interrogate behavioral representations in the mouse brain, we developed a fast deep-learning model for tracking 13 distinct points on the mouse face recorded from arbitrary camera angles. The model was just as accurate as state-of-the-art pose estimation tools while being several times faster, making it a powerful tool for closed-loop behavioral experiments. Next, we aligned facial key points across mice in order to train a universal model to predict neural activity from behavior. The universal mouse model could predict neural activity as well as a model fit to a single mouse, showing that neural representations of behaviors are conserved across mice. The latent states extracted from the universal model contained interpretable mouse behaviors.