Parallel Processing Using the PVM for Genetic Algorithms and Neural Networks

摘要

We describe in this paper the use of parallel processing for neural networks and genetic algorithms. We used in this research work the Parallel Virtual Machine (PVM), on a cluster of 16 processors, to achieve the performance that we needed for intelligent control applications. We tested different types of neural networks and genetic algorithms on the cluster to measure the efficiency and the accuracy of the implementation. We also considered in this paper the application of neural networks and genetic algorithms to the problem of controlling nonlinear dynamic plants.