Sciweavers

Share
ECAL
2005
Springer

Analysing the Evolvability of Neural Network Agents Through Structural Mutations

10 years 9 months ago
Analysing the Evolvability of Neural Network Agents Through Structural Mutations
This paper investigates evolvability of artificial neural networks within an artificial life environment. Five different structural mutations are investigated, including adaptive evolution, structure duplication, and incremental changes. The total evolvability indicator, Etotal, and the evolvability function through time, are calculated in each instance, in addition to other functional attributes of the system. The results indicate that incremental modifications to networks, and incorporating an adaptive element into the evolution process itself, significantly increases neural network evolvability within open-ended artificial life simulations.
Ehud Schlessinger, Peter J. Bentley, R. Beau Lotto
Added 27 Jun 2010
Updated 27 Jun 2010
Type Conference
Year 2005
Where ECAL
Authors Ehud Schlessinger, Peter J. Bentley, R. Beau Lotto
Comments (0)
books