NCLGNEJun 18, 2018

A Simple Reservoir Model of Working Memory with Real Values

arXiv:1806.06545v1
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of modeling working memory in cognitive neuroscience using reservoir computing, but it is incremental as it builds on existing ESN frameworks.

The study investigated whether an Echo State Network (ESN) can store and maintain real values from streamed input to act as a working memory unit and perform non-linear computations, finding that an explicit memory architecture improves performance.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes