An Artificial Neural Network Functionalized by Evolution - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

An Artificial Neural Network Functionalized by Evolution

Résumé

The topology of artificial neural networks has a significant effect on their performance. Characterizing efficient topology is a field of promising research in Artificial Intelligence. However, it is not a trivial task and it is mainly experimented on through convolutional neural networks. We propose a hybrid model which combines the tensor calculus of feed-forward neural networks with Pseudo-Darwinian mechanisms. This allows for finding topologies that are well adapted for elaboration of strategies, control problems or pattern recognition tasks. In particular, the model can provide adapted topologies at early evolutionary stages, and 'structural convergence', which can found applications in robotics, big-data and artificial life.

Dates et versions

hal-03681501 , version 1 (30-05-2022)

Identifiants

Citer

Fabien Furfaro, Avner Bar-Hen, Geoffroy C.B. Berthelot. An Artificial Neural Network Functionalized by Evolution. 2022. ⟨hal-03681501⟩
34 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More