Evolving Neural Networks with Interval Weights by Means of Genetic Algorithm
Hidehiko Okada · Journal of the Institute of Industrial Applications Engineers · 2013
In this paper, the author proposes an extension of genetic algorithm (GA) for evolving neural networks with interval-valued weights and biases. In the proposed extension, genotype values are not real numbers but intervals. Evolutionary processes in GA are extended so that the processes can handle interval-valued genotypes. Experimental results show that interval neural networks evolved by the proposed method can model target interval functions well despite the fact that no training data is explicitly provided.