A Simple Reservoir Model of Working Memory with Real Values

Anthony Strock (1) , Nicolas P. Rougier (1) , Xavier Hinaut (1)

1 Mnemosyne - Mnemonic Synergy

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 main-tain (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.

Domaines: Réseau de neurones [cs.NE]; Apprentissage [cs.LG]; Neurosciences [q-bio.NC]

Anthony Strock, Nicolas P. Rougier, Xavier Hinaut. A Simple Reservoir Model of Working Memory with Real Values. 2018 International Joint Conference on Neural Networks (IJCNN), Jul 2018, Rio de Janeiro, Brazil. ⟨10.1109/IJCNN.2018.8489262⟩. ⟨hal-01803594⟩