A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems - ENSTA Paris - École nationale supérieure de techniques avancées Paris Accéder directement au contenu
Article Dans Une Revue Cognitive Computation Année : 2016

A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems

Résumé

We present a biologically inspired architecture for incremental learning that remains resource-efficient even in the face of very high data dimensionalities (>1000) that are typically associated with perceptual problems. In particular, we investigate how a new perceptual (object) class can be added to a trained architecture without retraining, while avoiding the well-known catastrophic forgetting effects typically associated with such scenarios. At the heart of the presented architecture lies a generative description of the perceptual space by a self-organized approach which at the same time approximates the neighbourhood relations in this space on a two-dimensional plane. This approximation , which closely imitates the topographic organization of the visual cortex, allows an efficient local update rule for incremental learning even in the face of very high dimensionalities, which we demonstrate by tests on the well-known MNIST benchmark. We complement the model by adding a biologically plausible short-term memory system, allowing it to retain excellent classification accuracy even under incremental learning in progress. The short-term memory is additionally used to reinforce new data statistics by replaying previously stored samples during dedicated " sleep " phases.
Fichier principal
Vignette du fichier
article.pdf (3.08 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01418123 , version 1 (16-12-2016)

Identifiants

Citer

Alexander Gepperth, Cem Karaoguz. A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems. Cognitive Computation, 2016, 8, pp.924 - 934. ⟨10.1007/s12559-016-9389-5⟩. ⟨hal-01418123⟩
272 Consultations
1358 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More