Record Details

Mapping of neural network models onto massively parallel hierarchical computer systems

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Mapping of neural network models onto massively parallel hierarchical computer systems
 
Creator MAHAPATRA, S
 
Subject broadcasting
hierarchical systems
hypercube networks
learning
multilayer perceptrons
network topology
neural net architecture
 
Description Investigates the proposed implementation of neural networks on massively parallel hierarchical computer systems with hypernet topology. The proposed mapping scheme takes advantage of the inherent structure of hypernets to process multiple copies of the neural network in the different subnets, each executing a portion of the training set. Finally, the weight changes in all the subnets are accumulated to adjust the synaptic weights in all the copies. An expression is derived to estimate the time for all-to-all broadcasting, the principal mode of communication in implementing neural networks on parallel computers. This is later used to estimate the time required to execute various execution phases in the neural network algorithm, and thus to estimate the speedup performance of the hypernet in implementing neural networks.
 
Publisher IEEE
 
Date 2009-01-02T04:08:58Z
2011-11-28T06:13:09Z
2011-12-15T09:56:42Z
2009-01-02T04:08:58Z
2011-11-28T06:13:09Z
2011-12-15T09:56:42Z
1997
 
Type Article
 
Identifier Proceedings of the Fourth International Conference on High Performance Computing, Bangalore, India, 18-21 December 1997, 42-47
0-8186-8067-9
10.1109/HIPC.1997.634468
http://hdl.handle.net/10054/521
http://dspace.library.iitb.ac.in/xmlui/handle/10054/521
 
Language en