TY - GEN
T1 - Reliability characteristics of Hebbian-type associative memories in network implementations
AU - Chung, Pau Choo
AU - Krile, Thomas F.
PY - 1992
Y1 - 1992
N2 - The performance of Hebbian-type associative memories (HAMs) in the presence of faulty interconnections is examined, and equations for predicting network reliability are developed. Optical and VLSI implementations of HAMs are introduced, and the distributions of faulty interconnections in both implementations are discussed. The interconnection faults considered are the equivalent of open-circuit and short-circuit synaptic interconnections. Equations relating the probability of direct one-step convergence (Pdc) to the percentage of failed interconnections are developed for both types of interconnection faults. Monte Carlo simulations indicate that the equations considered here can estimate Pdc accurately. Based on the equations, network performance with failed interconnections can be predicted and trade-offs in network design can be determined before proceeding to implementation. The performance of networks with clustered failed interconnections is also discussed and compared with that of networks with randomly distributed faults. The present results are discussed from the implementation point of view.
AB - The performance of Hebbian-type associative memories (HAMs) in the presence of faulty interconnections is examined, and equations for predicting network reliability are developed. Optical and VLSI implementations of HAMs are introduced, and the distributions of faulty interconnections in both implementations are discussed. The interconnection faults considered are the equivalent of open-circuit and short-circuit synaptic interconnections. Equations relating the probability of direct one-step convergence (Pdc) to the percentage of failed interconnections are developed for both types of interconnection faults. Monte Carlo simulations indicate that the equations considered here can estimate Pdc accurately. Based on the equations, network performance with failed interconnections can be predicted and trade-offs in network design can be determined before proceeding to implementation. The performance of networks with clustered failed interconnections is also discussed and compared with that of networks with randomly distributed faults. The present results are discussed from the implementation point of view.
UR - http://www.scopus.com/inward/record.url?scp=0026631972&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0026631972&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0026631972
SN - 0780301641
T3 - Proceedings. IJCNN - International Joint Conference on Neural Networks
SP - 363
EP - 368
BT - Proceedings. IJCNN - International Joint Conference on Neural Networks
A2 - Anon, null
PB - Publ by IEEE
T2 - International Joint Conference on Neural Networks - IJCNN-91-Seattle
Y2 - 8 July 1991 through 12 July 1991
ER -