ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Parallel Implementation of Back-Propagation Algorithm in Networks of Workstations

Suresh, S and Omkar, SN and Mani, V (2005) Parallel Implementation of Back-Propagation Algorithm in Networks of Workstations. In: IEEE Transactions on Parallel and Distributed Systems, 16 (1). pp. 24-34.

[img] PDF
Parallel_implementation.pdf
Restricted to Registered users only

Download (785Kb) | Request a copy

Abstract

This paper presents an efficient mapping scheme for the multilayer perceptron (MLP) network trained using backpropagation (BP) algorithm on network of workstations (NOWs). Hybrid partitioning (HP) scheme is used to partition the network and each partition is mapped on to processors in NOWs. We derive the processing time and memory space required to implement the parallel BP algorithm in NOWs. The performance parameters like speed-up and space reduction factor are evaluated for the HP scheme and it is compared with earlier work involving vertical partitioning (VP) scheme for mapping the MLP on NOWs. The performance of the HP scheme is evaluated by solving optical character recognition (OCR) problem in a network of ALPHA machines. The analytical and experimental performance shows that the proposed parallel algorithm has better speed-up, less communication time, and better space reduction factor than the earlier algorithm. This paper also presents a simple and efficient static mapping scheme on heterogeneous system. Using divisible load scheduling theory, a closed-form expression for number of neurons assigned to each processor in the NOW is obtained. Analytical and experimental results for static mapping problem on NOWs are also presented

Item Type: Journal Article
Additional Information: Copyright 2005 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Keywords: Multilayer perceptron;back-propagation;network of workstation;optical character recognition;performance measures;divisible load theory
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering (Formerly, Aeronautical Engineering)
Date Deposited: 07 Mar 2007
Last Modified: 19 Sep 2010 04:17
URI: http://eprints.iisc.ernet.in/id/eprint/2512

Actions (login required)

View Item View Item