Learning and evolution in neural networks
Adaptive Behavior
Automatic definition of modular neural networks
Adaptive Behavior
Evolutionary algorithms in theory and practice: evolution strategies, evolutionary programming, genetic algorithms
Genetic Synthesis of Modular Neural Networks
Proceedings of the 5th International Conference on Genetic Algorithms
Interposing an Ontogenetic Model Between Genetic Algorithms and Neural Networks
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Creating Brain-Like Intelligence
Creating Brain-Like Intelligence
| Hi-index | 0.00 |
The interaction between learning and evolution has elicited muchinterest particularly among researchers who use evolutionaryalgorithms for the optimization of neural structures. In this article,we will propose an extension of the existing models by including adevelopmental phase – a growth process – of the neural network. In thisway, we are able to examine the dynamical interaction betweengenetic information and information learned duringdevelopment. Several measures are proposed to quantitatively examinethe benefits and the effects of such an overlap between learning andevolution. The proposed model, which is based on the recursiveencoding method for structure optimization of neural networks, isapplied to the problem domain of time series prediction. Furthermore,comments are made on problem domains which associate growingnetworks (size) during development with problems of increasing complexity.