Title :
Neural net based pattern recognition on the graph search machine
Author :
Na, Helen ; Glinski, Stephen
Author_Institution :
Illinois Univ., Urbana, IL, USA
Abstract :
The Hopfield net algorithm for pattern recognition has been implemented on a single GSM (graph search machine). The authors report on the methods used to implement the algorithm as well as on the algorithm performance as compared with competing architectures. It is shown that the GSM provides a viable alternative architecture for neural net research and development
Keywords :
graph theory; neural nets; pattern recognition; Hopfield net algorithm; algorithm performance; graph search machine; neural net development; neural net research; pattern recognition; Computer architecture; GSM; Image processing; Iterative algorithms; Neural networks; Pattern matching; Pattern recognition; Real time systems; Reduced instruction set computing; Research and development;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on
Conference_Location :
New York, NY
DOI :
10.1109/ICASSP.1988.197062
