Title :
Fault tolerant analysis of associative memories
Author :
Huang, Yo-Ping ; Gustafson, Donald
Author_Institution :
Dept. of Electr. Eng., Texas Tech. Univ., Lubbock, TX, USA
Abstract :
The performance of fault tolerant associative memories is investigated. Instead of presenting the results by simulation, the authors mathematically show that the one-step retrieval probability in most cases decreases with the increase in error ratio, number of error bits, and number of stored patterns. For the case of faulty resistance, however, the performance will surpass the nonerror situation under the positive weight change. This is not only true in the Hopfield interconnection topology but is also true in the exponential correlation case
Keywords :
content-addressable storage; neural nets; performance evaluation; probability; Hopfield interconnection topology; error bits; error ratio; exponential correlation; fault tolerant analysis; fault tolerant associative memories; neural nets; one-step retrieval probability; Associative memory; Fabrication; Fault tolerance; Manufacturing processes; Mathematical model; Neurons; Polynomials; Probes; Topology; Wires;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170335