RENNS-a reconfigurable computer system for artificial neural networks

Author

Solheim, Jon G. ; Myklebust, Gaute

Author_Institution

Div. of Comput. Syst. & Telematics, Norwegian Inst. of Technol., Trondheim, Norway

Volume

1

fYear

1995

fDate

19-21 Apr 1995

Firstpage

197

Abstract

An important property of a parallel computer system, is the interprocessor communication network. This paper addresses the reconfigurable aspects of the RENNS Communication Subsystem. The Subsystem is implemented in Logic Cell Arrays, LCAs, and is therefore reconfigurable to meet the requirements of different applications. Two of the training algorithms for Artificial Neural Networks implemented on RENNS, Back Propagation and Self-Organizing Maps, are briefly described, and it is shown how the communication system can be configured to speed up these algorithms

Keywords

backpropagation; learning (artificial intelligence); parallel algorithms; parallel architectures; reconfigurable architectures; self-organising feature maps; RENNS; artificial neural networks; back propagation; interprocessor communication network; logic cell arrays; parallel computer system; reconfigurable computer system; self-organizing maps; training algorithms; Artificial neural networks; Computational modeling; Computer architecture; Computer networks; Flip-flops; Hardware; Logic arrays; Logic devices; Neural networks; Physics computing;

fLanguage

English

Publisher

ieee

Conference_Titel

Algorithms and Architectures for Parallel Processing, 1995. ICAPP 95. IEEE First ICA/sup 3/PP., IEEE First International Conference on

Conference_Location

Brisbane, Qld.

Print_ISBN

0-7803-2018-2

Type

conf

DOI

10.1109/ICAPP.1995.472186

Filename

472186