menu
{ "item_title" : "Parallel Implementations of Backpropagation Neural Networks on Transputers", "item_author" : [" P. Saratchandran", "Shou King Foo", "Narasimman Sundararajan "], "item_description" : "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.", "item_img_path" : "https://covers2.booksamillion.com/covers/bam/9/81/022/654/9810226543_b.jpg", "price_data" : { "retail_price" : "56.00", "online_price" : "56.00", "our_price" : "56.00", "club_price" : "56.00", "savings_pct" : "0", "savings_amt" : "0.00", "club_savings_pct" : "0", "club_savings_amt" : "0.00", "discount_pct" : "10", "store_price" : "" } }
Parallel Implementations of Backpropagation Neural Networks on Transputers|P. Saratchandran

Parallel Implementations of Backpropagation Neural Networks on Transputers : A Study of Training Set Parallelism

local_shippingShip to Me
On Order. Usually ships in 2-4 weeks
FREE Shipping for Club Members help

Overview

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.

This item is Non-Returnable

Details

  • ISBN-13: 9789810226541
  • ISBN-10: 9810226543
  • Publisher: World Scientific Publishing Company
  • Publish Date: July 1996
  • Page Count: 220

Related Categories

You May Also Like...

    1

BAM Customer Reviews