brAIn Seminar - David Lipshutz

— 4:30pm

Location:
In Person and Virtual - ET - Baker Hall 340A and Zoom

Speaker:
DAVID LIPSHUTZ, Assistant Professor (Incoming), Department of Neuroscience, Baylor College of Medicine
https://lipshutzlab.com/team

Comparing image representations in terms of their local geometry

Image representations (artificial or biological) are often compared in terms of their global geometry; however, representations with similar global structure can have strikingly different local geometries. Here, we propose a framework for comparing a set of image representations in terms of their local geometries. 

We quantify the local geometry of a representation using the Fisher information matrix, a standard statistical tool for characterizing the sensitivity to local stimulus distortions, and use this as a substrate for a metric on the local geometry in the vicinity of a base image. This metric may then be used to optimally differentiate a set of models, by finding a pair of "principal distortions" that maximize the variance of the models under this metric. We use this framework to compare a set of simple models of the early visual system, identifying a novel set of image distortions that allow immediate comparison of the models by visual inspection. 

In a second example, we apply our method to a set of deep neural network models and reveal differences in the local geometry that arise due to architecture and training types. These examples highlight how our framework can be used to probe for informative differences in local sensitivities between complex computational models, and suggest how it could be used to compare model representations with human perception. 

— 

David Lipshutz is an incoming assistant professor of Neuroscience at Baylor College of Medicine. He's currently an associate research scientist at the Flatiron Institute where he works with Eero Simoncelli and Dmitri Chklovskii. Prior to working in Neuroscience, he received his Ph.D. in mathematics from UCSD and held postdoctoral positions at Brown University (Applied Math) and the Technion (Electrical Engineering). Additional Information

Communal Viewing in Baker 340A and Zoom Participation.  See announcement.

Event Website:
https://brain.andrew.cmu.edu/seminar