Automatic Generation of Neural Network Architecture Using Evolutionary Computation
This book describes 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 neural network. It is the usual practice to use trial and error to find a suitable neural network architecture for a given problem. The process of trial and error 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.An overview of the field of evolutionary computation is presented, together with the biological background from which the field was inspired. The most commonly used approaches to a mathematical foundation of the field of genetic algorithms are given, as well as an overview of the hybridization between evolutionary computation and neural networks. Experiments on the 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 algorithm for a feedforward neural network is also investigated.
What people are saying - Write a review
We haven't found any reviews in the usual places.
THE BIOLOGICAL BACKGROUND
MATHEMATICAL FOUNDATIONS OF GENETIC ALGORITHMS
HYBRIDISATION OF EVOLUTIONARY COMPUTATION
USING GENETIC PROGRAMMING TO GENERATE NEURAL
Other editions - View all
ADFs alphabet Artificial neural networks average Baldwin Effect binary coding Building Block Hypothesis cell chromosome length competing conventions complexity connectivity matrix convergence corresponding crossover and mutation crossover operator defined direct encoding scheme epistasis error evolution evolutionary computation evolutionary theory example feedforward neural network Figure fitness function fitness values gamete gene genetic algorithm genetic operators genetic programming Genitor-type genotype global optimum GPNN grammar encoding hidden neurons hill-climbing algorithm implemented input layer linear matrix grammar scheme mechanism mutation operator natural selection needed neural network architecture neural network structure normal number of neurons offspring optimal organisms output neurons parents performance phenotype pruning random real-valued coding reproduction resulting rewriting cycles rewriting rules schema H Schema Theorem schemata search space selective pressure set of weights simply solution standard genetic algorithm Steady State Genetic SUGAL supervised learning target output topology training data training set weight optimisation weight space weight transmission XOR problem