Forming Neural Networks Through Efficient and Adaptive Coevolution
- 1 December 1997
- journal article
- Published by MIT Press in Evolutionary Computation
- Vol. 5 (4) , 373-399
- https://doi.org/10.1162/evco.1997.5.4.373
Abstract
This article demonstrates the advantages of a cooperative, coevolutionary search in difficult control problems. The symbiotic adaptive neuroevolution (SANE) system coevolves a population of neurons that cooperate to form a functioning neural network. In this process, neurons assume different but overlapping roles, resulting in a robust encoding of control behavior. SANE is shown to be more efficient and more adaptive and to maintain higher levels of diversity than the more common network-based population approaches. Further empirical studies illustrate the emergent neuron specializations and the different roles the neurons assume in the population.Keywords
This publication has 9 references indexed in Scilit:
- Intelligence without representationPublished by Elsevier ,2003
- Evolving artificial neural networks to control chaotic systemsPhysical Review E, 1997
- Efficient reinforcement learning through symbiotic evolutionMachine Learning, 1996
- Coevolutionary ComputationArtificial Life, 1995
- Is a Learning Classifier System a Type of Neural Network?Evolutionary Computation, 1994
- Searching for Diverse, Cooperative Populations with Genetic AlgorithmsEvolutionary Computation, 1993
- Genetic Reinforcement Learning for Neurocontrol ProblemsMachine Learning, 1993
- Learning sequential decision rules using simulation models and competitionMachine Learning, 1990
- IntroductionArtificial Intelligence, 1990