Exploring continual learning strategies in artificial neural networks through graph-based analysis of connectivity: insights from a brain-inspired perspective - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2023

Exploring continual learning strategies in artificial neural networks through graph-based analysis of connectivity: insights from a brain-inspired perspective

Abstract

Artificial Neural Networks (ANNs) aim at mimicking information processing in biological networks. In cognitive neuroscience, graph modeling is a powerful framework widely used to study brain structural and functional connectivity. Yet, the extension of graph modeling to ANNs has been poorly explored especially in term of functional connectivity (i.e. the contextual change of the activity's units in networks). From the perspective of designing more robust and interpretable ANNs, we study how a brain-inspired graph-based approach can be extended and used to investigate their properties and behaviors. We focus our study on different continual learning strategies inspired by the human brain and modeled with ANNs. We show that graph modeling offers a simple and elegant framework to deeply investigate ANNs, compare their performances and explore deleterious behaviors such as catastrophic forgetting.
Fichier principal
Vignette du fichier
Exploring_Continual_Learning_Strategies_preprint.pdf (2.94 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04284871 , version 1 (14-11-2023)

Licence

Identifiers

  • HAL Id : hal-04284871 , version 1

Cite

Lucrezia Carboni, Dwight Nwaigwe, Marion Mainsant, Raphaël Bayle, Marina Reyboz, et al.. Exploring continual learning strategies in artificial neural networks through graph-based analysis of connectivity: insights from a brain-inspired perspective. 2023. ⟨hal-04284871⟩
146 View
76 Download

Share

Gmail Mastodon Facebook X LinkedIn More