Please use this identifier to cite or link to this item:
Title: Mapping of backpropagation learning onto distributed memory multiprocessors
Keywords: Backpropagation
Feedforward Neural Nets
Parallel Algorithms
Pipeline Processing
Transputer Systems
Issue Date: 1995
Publisher: IEEE
Citation: Proceedings of the IEEE First International Conference on Algorithms and Architectures for Parallel Processing (V 1), Brisbane, Australia, 19-2 April 1995, 217-226
Abstract: This paper presents a mapping scheme for parallel pipelined execution of the Backpropagation Learning Algorithm on distributed memory multiprocessors (DMMs). The proposed implementation exhibits training set parallelism that involves batch updating. Simple algorithms have been presented, which allow the data transfer involved in both forward and backward executions phases of the backpropagation algorithm to be carried out with a small communication overhead. The effectiveness of our mapping has been illustrated, by estimating the speedup of a proposed implementation on an array of T-805 transputers.
URI: 10.1109/ICAPP.1995.472188
ISBN: 0-7803-2018-2
Appears in Collections:Proceedings papers

Files in This Item:
File Description SizeFormat 
472188.pdf536.02 kBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.