English

A Simple Reservoir Model of Working Memory with Real Values

Neurons and Cognition 2018-06-19 v1 Machine Learning Neural and Evolutionary Computing

Abstract

The prefrontal cortex is known to be involved in many high-level cognitive functions, in particular, working memory. Here, we study to what extent a group of randomly connected units (namely an Echo State Network, ESN) can store and maintain (as output) an arbitrary real value from a streamed input, i.e. can act as a sustained working memory unit. Furthermore, we explore to what extent such an architecture can take advantage of the stored value in order to produce non-linear computations. Comparison between different architectures (with and without feedback, with and without a working memory unit) shows that an explicit memory improves the performances.

Keywords

Cite

@article{arxiv.1806.06545,
  title  = {A Simple Reservoir Model of Working Memory with Real Values},
  author = {Anthony Strock and Nicolas Rougier and Xavier Hinaut},
  journal= {arXiv preprint arXiv:1806.06545},
  year   = {2018}
}
R2 v1 2026-06-23T02:32:49.590Z