Skip to Main content Skip to Navigation
Journal articles

A Bio-Inspired Incremental Learning Architecture for Applied Perceptual Problems

Alexander Gepperth 1, 2 Cem Karaoguz 2
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : 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.
Document type :
Journal articles
Complete list of metadata

Cited literature [25 references]  Display  Hide  Download
Contributor : Alexander Gepperth <>
Submitted on : Friday, December 16, 2016 - 1:04:21 PM
Last modification on : Monday, December 9, 2019 - 4:44:05 PM


Files produced by the author(s)




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



Record views


Files downloads