AUTHOR=Zavatone-Veth Jacob A. , Bordelon Blake , Pehlevan Cengiz 

TITLE=Summary statistics of learning link changing neural representations to behavior

JOURNAL=Frontiers in Neural Circuits

VOLUME=Volume 19 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/neural-circuits/articles/10.3389/fncir.2025.1618351

DOI=10.3389/fncir.2025.1618351

ISSN=1662-5110

ABSTRACT=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.