Stepwise transition from direct encoding to artificial ontogeny in neuroevolution

Authors:
Benjamin Inden
Affiliations:
Max Planck Institute for Mathematics in the Sciences
Venue:
ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
Year:
2007

Citing 3
Cited 0

Evolving neural networks through augmenting topologies

Evolutionary Computation
A Taxonomy for artificial embryogeny

Artificial Life
Efficient evolution of neural networks through complexification

Efficient evolution of neural networks through complexification

Quantified Score

Hi-index	0.00

Visualization

Abstract

There is a gap between neuroevolution systems employing artificial ontogeny and those being able to solve difficult control tasks. The NEON system builds on ideas of the well known NEAT neuroevolution system to make possible a stepwise transition from a direct encoding to complex genetic architectures using developmental processes.