Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks

We study the learning dynamics and the representations emerging in recurrent neural networks (RNNs) trained to integrate one or multiple temporal signals. Combining analytical and numerical investigations, we characterize the conditions under which an RNN with neurons learns to integrate scalar sign...

Full description

Bibliographic Details

Published in:	Neural computation Vol. 33; no. 4; p. 1
Main Authors:	Fanthomme, Arnaud, Monasson, Rémi
Format:	Journal Article
Language:	English
Published:	United States 26.03.2021
ISSN:	1530-888X, 1530-888X
Online Access:	Get more information
Tags:	Add Tag No Tags, Be the first to tag this record!