Neural representational geometry underlies few-shot concept learning

DOI10.1073/PNAS.2200800119MaRDI QIDQ7017888zbMATH OpenFDO

Authors Ben Sorscher, Surya Ganguli, Haim Sompolinsky

Publication date 5 March 2025

Published in Proceedings of the National Academy of Sciences of the United States of America (Search for Journal in Brave)

Copyright license Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Full work available at URL https://doi.org/10.1073/PNAS.2200800119

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Physiology (general) (92C30)

Cited in

(3)

• On the ability of deep networks to learn symmetries from data: a neural kernel theory
• Robust query performance prediction for dense retrievers via adaptive disturbance generation
• Statistical mechanics of deep learning

This page was built for publication: Neural representational geometry underlies few-shot concept learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7017888)