Augmenting Machine Learning with Flexible Episodic Memory - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Augmenting Machine Learning with Flexible Episodic Memory

Etendre l'apprentissage machine avec la mémoire épisodique flexible

Hugo Chateau-Laurent
Frédéric Alexandre

Abstract

A major cognitive function is often overlooked in artificial intelligence research: episodic memory. In this paper, we relate episodic memory to the more general need for explicit memory in intelligent processing. We describe its main mechanisms and its involvement in a variety of functions, ranging from concept learning to planning. We set the basis for a computational cognitive neuroscience approach that could result in improved machine learning models. More precisely, we argue that episodic memory mechanisms are crucial for contextual decision making, generalization through consolidation and prospective memory.
Fichier principal
Vignette du fichier
NCTA_2021_16_CR.pdf (690.95 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03359384 , version 1 (30-09-2021)

Identifiers

  • HAL Id : hal-03359384 , version 1

Cite

Hugo Chateau-Laurent, Frédéric Alexandre. Augmenting Machine Learning with Flexible Episodic Memory. 13th International Joint Conference on Computational Intelligence, Oct 2021, Valletta, Malta. ⟨hal-03359384⟩
173 View
249 Download

Share

Gmail Mastodon Facebook X LinkedIn More