Augmenting Machine Learning with Flexible Episodic Memory

Hugo Chateau-Laurent, Hugo Chateau-Laurent, Hugo Chateau-Laurent, Frédéric Alexandre, Frédéric Alexandre, Frédéric Alexandre

2021

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.

Paper Citation

in Harvard Style

Chateau-Laurent H. and Alexandre F. (2021). Augmenting Machine Learning with Flexible Episodic Memory. In Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA; ISBN 978-989-758-534-0, SciTePress, pages 326-333. DOI: 10.5220/0010674600003063

in Bibtex Style

@conference{ncta21,
author={Hugo Chateau-Laurent and Frédéric Alexandre},
title={Augmenting Machine Learning with Flexible Episodic Memory},
booktitle={Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA},
year={2021},
pages={326-333},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010674600003063},
isbn={978-989-758-534-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Joint Conference on Computational Intelligence (IJCCI 2021) - Volume 1: NCTA
TI - Augmenting Machine Learning with Flexible Episodic Memory
SN - 978-989-758-534-0
AU - Chateau-Laurent H.
AU - Alexandre F.
PY - 2021
SP - 326
EP - 333
DO - 10.5220/0010674600003063
PB - SciTePress