Distributed memory systems for simulating artificial neural networks

Patnaik, LM and Kumar, Mohan J (1993) Distributed memory systems for simulating artificial neural networks. In: Computers & Electrical Engineering, 19 (6). pp. 431-443.

PDF DISTRIBUTED-377.pdf Restricted to Registered users only Download (956kB) | Request a copy

Abstract

In executing tasks involving intelligent information processing, the human brain performs better than the digital computer. The human brain derives its power from a large number $[O(10^{11})]$ of neurons which are interconnected by a dense interconnection network $[O(10^5)$ connections per neuron]. Artificial neural network (ANN) paradigms adopt the structure of the brain to try to emulate the intelligent information processing methods of the brain. ANN techniques are being employed to solve problems in areas such as pattern recognition, and robotic processing. Simulation of ANNs involves implementation of large number of neurons and a massive interconnection network. In this paper, we discuss various simulation models of ANNs and their implementation on distributed memory systems. Our investigations reveal that communication-efficient networks of distributed memory systems perform better than other topologies in implementing ANNs.

Item Type:	Journal Article
Publication:	Computers & Electrical Engineering
Publisher:	Elsevier
Additional Information:	The copyright of this article belongs to Elsevier.
Keywords:	Artificial neural networks;Distributed memory systems;Total exchange;Multinode broadcase;Hierarchical network of hypercubes
Department/Centre:	Division of Electrical Sciences > Computer Science & Automation
Date Deposited:	26 Sep 2006
Last Modified:	19 Sep 2010 04:31
URI:	http://eprints.iisc.ac.in/id/eprint/8408

Actions (login required)

View Item