DocumentCode
3354890
Title
Fault tolerant neural networks in optimization problems
Author
Koyanagi, Y. ; Tohma, Y.
Author_Institution
Dept. of Comput. Sci., Tokyo Inst. of Technol., Japan
fYear
1992
fDate
8-10 July 1992
Firstpage
412
Lastpage
418
Abstract
The authors discuss the influence of stuck-at faults in neural networks for solving optimization problems. They use a Hopfield model of a neural network, applying it to the traveling salesman problem of five cities. The asymmetric nature of fault tolerance of the network against stuck-at-zero and stuck-at-one faults is revealed. A method to alleviate this asymmetry and enhance the fault tolerance greatly is proposed.<>
Keywords
Hopfield neural nets; fault tolerant computing; operations research; optimisation; Hopfield model; fault tolerance; five cities; neural networks; optimization problems; stuck-at faults; stuck-at-one; stuck-at-zero; traveling salesman problem; Artificial neural networks; Cities and towns; Computer science; Fault tolerance; Hardware; Hopfield neural networks; Intelligent networks; Neural networks; Recurrent neural networks; Traveling salesman problems;
fLanguage
English
Publisher
ieee
Conference_Titel
Fault-Tolerant Computing, 1992. FTCS-22. Digest of Papers., Twenty-Second International Symposium on
Conference_Location
Boston, MA, USA
Print_ISBN
0-8186-2875-8
Type
conf
DOI
10.1109/FTCS.1992.243594
Filename
243594
Link To Document