Parallel Implementations of Backpropagation Neural Networks on Transputers

Parallel Implementations of Backpropagation Neural Networks on Transputers

A Study of Training Set Parallelism

eBook - 1996
Rate this:
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.
Publisher: Singapore ; River Edge, NJ : World Scientific, Ă1996
ISBN: 9789812814968
Characteristics: 1 online resource (xviii, 202 pages)
Additional Contributors: Foo, Shou King
Sundararajan, N.


From the critics

Community Activity


Add a Comment

There are no comments for this title yet.

Age Suitability

Add Age Suitability

There are no age suitabilities for this title yet.


Add a Summary

There are no summaries for this title yet.


Add Notices

There are no notices for this title yet.


Add a Quote

There are no quotes for this title yet.

Explore Further

Subject Headings


Find it at NPL

To Top