A parallel simulator to build distributed neural algorithms

Author

Boniface, Yann

Author_Institution

INRIA, INRIA, Vandoeuvre-les-Nancy, France

Volume

4

fYear

2001

fDate

2001

Firstpage

2399

Abstract

The aim of the paper is to present a parallel simulator that allows one to use distributed algorithm to develop artificial neural networks. We developed an efficient parallel simulator to implement artificial neural networks. This simulator makes use of the parallel properties of connectionist models to make an efficient parallel implementation onto general purpose shared memory MIMD computers. Therefore, this simulator naturally leads to build (learning and generalising) neural algorithms that respect the large natural parallel aspects of these models

Keywords

distributed programming; generalisation (artificial intelligence); learning (artificial intelligence); neural nets; parallel algorithms; simulation; connectionist models; distributed neural algorithms; generalisation; learning; neural networks; parallel simulator; shared memory MIMD computers; Artificial neural networks; Biological system modeling; Biology computing; Brain modeling; Computational modeling; Computer networks; Computer simulation; Concurrent computing; Neurons; Parallel processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on

Conference_Location

Washington, DC

ISSN

1098-7576

Print_ISBN

0-7803-7044-9

Type

conf

DOI

10.1109/IJCNN.2001.938742

Filename

938742