Vonk E., Jain L.C., Johnson R.P. Automatic Generation of Neural Network Architecture Using Evolutionary Computation

World Scientific, 1999, -194 p.This book presents our research on the application of evolutionary computation in the automatic generation of a neural network architecture. The architecture has a significant influence on the performance of the network. It is the usual practice to use trial and error to find a suitable neural network architecture for a given problem. This method is not only time consuming but may not generate an optimal network. The use of evolutionary computation is a step towards automation in neural network architecture generation. In this book, an overview of the field of evolutionary computation is given together with the biological background from which the field was inspired. The most commonly used approaches towards a mathematical foundation of the field of genetic algorithms is given, as well as an overview of the hybridisations between evolutionary computation and neural networks. Experiments concerning an implementation of automatic neural network generation using genetic programming and one using genetic algorithms are described, and the efficacy of genetic algorithms as a learning technique for a feedforward neural network is also investigated.Artificial Neural Networks
Evolutionary Computation
The Biological Background
Mathematical Foundations of Genetic Algorithms
Implementing GAs
Hybridisation of Evolutionary Computation and Neural Networks
Using Genetic Programming to Generate Neural Networks
Using a GA to Optimise the Weights of a Neural Network
Using a GA with Grammar Encoding to Generate Neural Networks
Conclusions and Future Directions