English

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}
}
R2 v1 2026-06-23T10:05:40.774Z