The Evolution of Artificial Neurogenesis

Dennis G. Wilson (1) , Sylvain Cussat-Blanc (1, 2) , Hervé Luga (1, 3)

1 IRIT-REVA - Real Expression Artificial Life
2 UT Capitole - Université Toulouse Capitole
3 UT2J - Université Toulouse - Jean Jaurès

Evolutionary development as a strategy for the design of artificial neural networks is an enticing idea, with possible inspiration from both biology and existing indirect representations. A growing neural network can not only optimize towards a specific goal, but can also exhibit plasticity and regeneration. Furthermore, a generative system trained in the optimization of the resultant neural network in a reinforcement learning environment has the capability of on-line learning after evolution in any reward-driven environment. In this abstract, we outline the motivation for and design of a generative system for artificial neural network design.

Mots clés: Neural networks; Cognitive science; Artificial intelligence

Domaines: Synthèse d'image et réalité virtuelle [cs.GR]; Traitement du signal et de l'image [eess.SP]; Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Intelligence artificielle [cs.AI]

Dennis G. Wilson, Sylvain Cussat-Blanc, Hervé Luga. The Evolution of Artificial Neurogenesis. Genetic and Evolutionary Computation Conference Companion (GECCO 2016), Jul 2016, Denver, United States. pp. 1047-1048. ⟨hal-01782552⟩