This book presents a systematic approach to parallel implementation of feedforward neural networks on an array of transputers. The emphasis is on backpropagation learning and training set parallelism. Using systematic analysis, a theoretical model has been developed for the parallel implementation. The model is used to find the optimal mapping to minimize the training time for large backpropagation neural networks. The model has been validated experimentally on several well known benchmark problems. Use of genetic algorithms for optimizing the performance of the parallel implementations is described. Guidelines for efficient parallel implementations are highlighted.
Dieses Ebook kaufen – und ein weitere GRATIS erhalten!
Sprache Englisch ● Format PDF ● Seiten 220 ● ISBN 9789812814968 ● Dateigröße 21.4 MB ● Verlag World Scientific Publishing Company ● Ort Singapore ● Land SG ● Erscheinungsjahr 1996 ● herunterladbar 24 Monate ● Währung EUR ● ID 2447347 ● Kopierschutz Adobe DRM
erfordert DRM-fähige Lesetechnologie