Summary statistics of learning link changing neural representations to behavior

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zavatone-Veth, Jacob A., Bordelon, Blake, Pehlevan, Cengiz
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911138659172352
author Zavatone-Veth, Jacob A.
Bordelon, Blake
Pehlevan, Cengiz
author_facet Zavatone-Veth, Jacob A.
Bordelon, Blake
Pehlevan, Cengiz
contents How can we make sense of large-scale recordings of neural activity across learning? Theories of neural network learning with their origins in statistical physics offer a potential answer: for a given task, there are often a small set of summary statistics that are sufficient to predict performance as the network learns. Here, we review recent advances in how summary statistics can be used to build theoretical understanding of neural network learning. We then argue for how this perspective can inform the analysis of neural data, enabling better understanding of learning in biological and artificial neural networks.
format Preprint
id arxiv_https___arxiv_org_abs_2504_16920
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Summary statistics of learning link changing neural representations to behavior
Zavatone-Veth, Jacob A.
Bordelon, Blake
Pehlevan, Cengiz
Neurons and Cognition
How can we make sense of large-scale recordings of neural activity across learning? Theories of neural network learning with their origins in statistical physics offer a potential answer: for a given task, there are often a small set of summary statistics that are sufficient to predict performance as the network learns. Here, we review recent advances in how summary statistics can be used to build theoretical understanding of neural network learning. We then argue for how this perspective can inform the analysis of neural data, enabling better understanding of learning in biological and artificial neural networks.
title Summary statistics of learning link changing neural representations to behavior
topic Neurons and Cognition
url https://arxiv.org/abs/2504.16920