[WTI-trainee] Grace Lindsay Talk, Monday Nov 27th, 12:30 PM "Analyzing artificial neural networks to understand the brain"

[Natalia Castelo Branco Matos]

We are thrilled to announce an upcoming session of our neurophilosophy
seminar series featuring Professor Grace Lindsay from New York University.

🎙️ Talk Title: "Analyzing artificial neural networks to understand the
brain"
📅 Date: Mon, November 27th, 2023
🕒 Time: 12:30 - 2:00 PM
📍 Location: 100 College Street, Room 1167

About the Speaker: Dr. Grace Lindsay is an Assistant Professor of
Psychology and Data Science at New York University, with a background that
includes a BS in Neuroscience from the University of Pittsburgh and a PhD
from Columbia University's Center for Theoretical Neuroscience. Her
research is focused on using artificial neural networks to understand brain
function, particularly in the realms of attention and sensory processing.
Dr. Lindsay also explores the efficacy of current tools in interpreting
neural activity. Additionally, Dr. Lindsay has authored a popular science
book titled "Models of the Mind", where she delves into the intersection of
mathematics, physics, engineering, and neuroscience. If you are interested
in learning more about her work, please visit Dr. Lindsay's personal
webpage.

Talk Abstract: In the first part of this talk, I will present work showing
that artificial neural networks with recurrent connections can replicate
broad behavioral patterns associated with dynamic visual object recognition
in humans. An analysis of these networks shows that different types of
recurrence use different strategies to solve the object recognition
problem. The analysis of these networks, however, introduces another
question: are the tools of neuroscience suitable for understanding complex
distributed information processing systems? In the second part of this
talk, I will discuss—and solicit feedback on—a research plan for testing a
wide range of analysis tools frequently applied to neural data on
artificial neural networks. I will present the motivation for this approach
as well as the form the results could take and how this would benefit
neuroscience and the field of interpretable AI.

Yours Truly,
APHINE Leadership
Alec Sheffield (alec.sheffield at yale.edu)
Clayton Barnes (clayton.barnes at yale.edu)
Natalia Castelo Branco Matos (natalia.castelobrancomatos at yale.edu)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.yale.edu/mailman/private/wti-trainee/attachments/20231126/db2f3ddf/attachment.html>