The Parallel Genetic Algorithm for Construction of Technological Objects Neural Network Models

Abstract

The parallel genetic algorithms implementation for neural networks models construction is discussed. The modification of this global optimization algorithm is proposed. The artificial neural networks are effective instrument to solve most problems of technological objectives and processes modelling. The article describes the aspects of genetic algorithms implementation for neural networks structure-parametric synthesis. It is offered to use different parallelization technique of genetic algorithm to increase computing performance. It is proposed to modify the standard multipopular parallel genetic algorithm adding its base topology dynamic adaptation. This approach allows to make effective algorithm with minimal computational difficulty. The algorithm modification shows best results, when implemented in computer network.