Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network
Adaptation and Self-Organizing Systems
2020-07-01 v1 Neural and Evolutionary Computing
Neurons and Cognition
Abstract
Memories in neural system are shaped through the interplay of neural and learning dynamics under external inputs. By introducing a simple local learning rule to a neural network, we found that the memory capacity is drastically increased by sequentially repeating the learning steps of input-output mappings. The origin of this enhancement is attributed to the generation of a Psuedo-inverse correlation in the connectivity. This is associated with the emergence of spontaneous activity that intermittently exhibits neural patterns corresponding to embedded memories. Stablization of memories is achieved by a distinct bifurcation from the spontaneous activity under the application of each input.
Cite
@article{arxiv.1906.11770,
title = {Repeated sequential learning increases memory capacity via effective decorrelation in a recurrent neural network},
author = {Tomoki Kurikawa and Omri Barak and Kunihiko Kaneko},
journal= {arXiv preprint arXiv:1906.11770},
year = {2020}
}