Share Email Print

Proceedings Paper

General neural computer architecture and its ANN-based task assignment method for parallel-distributed processing
Author(s): Hu Chao; Sylvian R. Ray; Nanning Zheng
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

A new DSP-based neural simulating computer architecture and its ANN-based assignment method for parallel distributed processing are proposed. The hardware of the proposed neural simulating computer can be reconfigured in terms of a variety of research interests and requirements of pattern recognition. The software programming environment utilizes an intelligent compiler to perform static task assignment in both the cases of single-task muliprocessor and multitask processor. An improved Hopfield neural network which can converge to global optical solution is employed by the compiler to map different tasks or neurons to their corresponding real processors. An approach of introducing hidden layer to increase the computation ability of the neural simulating computer is also developed. Finally, a proof is given which shows that the use of improved Hopfield algorithm and the modification to network structure doesn't change the intrinsic properties of the original network.

Paper Details

Date Published: 16 June 1995
PDF: 8 pages
Proc. SPIE 2488, Visual Information Processing IV, (16 June 1995); doi: 10.1117/12.211998
Show Author Affiliations
Hu Chao, Univ. of Illinois/Urbana-Champaign (United States)
Sylvian R. Ray, Univ. of Illinois/Urbana-Champaign (United States)
Nanning Zheng, Xi'an Jiaotong Univ. (China)

Published in SPIE Proceedings Vol. 2488:
Visual Information Processing IV
Friedrich O. Huck; Richard D. Juday, Editor(s)

© SPIE. Terms of Use
Back to Top