[Re] How Attention Can Create Synaptic Tags for the Learning of Working Memories in Sequential Tasks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles The ReScience journal Year : 2016

[Re] How Attention Can Create Synaptic Tags for the Learning of Working Memories in Sequential Tasks

Erwan Le Masson
  • Function : Author
Frédéric Alexandre

Abstract

The reference paper introduces a new reinforcement learning model called Attention- Gated MEmory Tagging (AuGMEnT). The results presented suggest new approaches in understanding the acquisition of tasks requiring working memory and attentional feedback, as well as biologically plausible learning mechanisms. The model also improves on previous reinforcement learning schemes by allowing tasks to be expressed more naturally as a sequence of inputs and outputs. A Python implementation of the model is available on the author’s GitHub page which helped to verify the correctness of the computations. The script written for this replication also uses Python along with NumPy.
Fichier principal
Vignette du fichier
Le_Masson-Alexandre-2016.pdf (200.65 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-01418735 , version 1 (16-12-2016)

Identifiers

Cite

Erwan Le Masson, Frédéric Alexandre. [Re] How Attention Can Create Synaptic Tags for the Learning of Working Memories in Sequential Tasks. The ReScience journal, 2016, 2 (1), ⟨10.1371/journal.pcbi.1004060⟩. ⟨hal-01418735⟩
113 View
166 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More