Record Details

Mapping of backpropagation learning onto distributed memory multiprocessors

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Mapping of backpropagation learning onto distributed memory multiprocessors
 
Creator MAHAPATRA, S
MAHAPATRA, RN
 
Subject backpropagation
feedforward neural nets
parallel algorithms
pipeline processing
transputer systems
 
Description 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.
 
Publisher IEEE
 
Date 2009-01-02T04:08:22Z
2011-11-28T03:39:39Z
2011-12-15T09:56:11Z
2009-01-02T04:08:22Z
2011-11-28T03:39:39Z
2011-12-15T09:56:11Z
1995
 
Type Article
 
Identifier Proceedings of the IEEE First International Conference on Algorithms and Architectures for Parallel Processing (V 1), Brisbane, Australia, 19-2 April 1995, 217-226
0-7803-2018-2
10.1109/ICAPP.1995.472188
http://hdl.handle.net/10054/519
http://dspace.library.iitb.ac.in/xmlui/handle/10054/519
 
Language en