Ben Sorscher

Publications

Neural representational geometry underlies few-shot concept learning.
B Sorscher, S Ganguli, H Sompolinsky.
PNAS 2022

A unified theory for the computational and mechanistic origins of grid cells.
B Sorscher*, G Mel*, SA Ocko, L Giocomo, S Ganguli.
Neuron 2022

A theory of learning with constrained weight-distribution.
W Zhong, B Sorscher, DD Lee, H Sompolinsky.
NeurIPS 2022

Explaining heterogeneity in medial entorhinal cortex with task-driven neural networks.
A Nayebi, A Attinger, M Campbell, K Hardcastle, I Low, CS Mallory, G Mel, B Sorscher, AH Williams, S Ganguli, L Giocomo, D Yamins.
NeurIPS spotlight 2021

A unified theory for the origin of grid cells through the lens of pattern formation.
B Sorscher*, G Mel*, S Ganguli, SA Ocko.
NeurIPS spotlight 2019

Conference abstracts

A theory of weight distribution-constrained learning.
W Zhong*, B Sorscher*, DD Lee, H Sompolinsky. APS March Meeting 2022.

Understanding the emergence of hexagonal grid cells in networks trained to path integrate.
G Mel*, B Sorscher*, S Ocko, S Ganguli. COSYNE 2020.

A theory of learning with a constrained weight distribution.
B Sorscher*, W Zhong*, DD Lee, H Sompolinsky. COSYNE 2020.

Education

Harvard University      A.B., Physics and Mathematics, 2018

Harvard University      A.M., Physics, 2018

Stanford University      Ph.D. candidate, Applied Physics, 2023

Teaching

• Methods in computational neuroscience, Woods Hole, 2022.
• Harvard Summer Undergraduate Research Village, 2018
• Eng-Sci 123, Fluid Mechanics and Transport Processes, Harvard University, 2017
• Physics 15c, Harvard University, 2016
• Math 23a, Harvard University, 2015
• Math 23b, Harvard University, 2015

US mail: Ben Sorscher
         290 Jane Stanford Way
         Stanford, CA 94305
Email:   bsorsch@gmail.com