Characteristics of Hebbian-Type Associative Memories Having Faulty Interconnections

Pau Choo Chung, Thomas F. Krile

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The performance of Hebbian-type associative memories (HAM's) in the presence of faulty interconnections is examined and equations for predicting network reliability are developed. The interconnection faults considered are the equivalents of open-circuit and short-circuit synaptic interconnections (analogously, opaque or clear weight mask elements in optical implementations). Our results show that a network with open-circuit interconnection faults has a higher probability of direct convergence, Pdc, than a network with short-circuit interconnection faults when the fraction of failed interconnections, p, is small and the short-circuit signal, G, is large. Our results are also extended to the case where network attraction radius is considered. During the analysis, a HAM is assumed to have a high probability of correct recall; i.e., memory storage is within its capacity. The individual neuron updating in an asynchronous network is assumed to occur in sequential order. Using these assumptions, it was found that the expected numbers of neurons having b. b - 1, b - 2.….1 input error bits in their state update are equal. Because of the capability of error correction, an asynchronous HAM is also found to have a higher Pdc than a synchronous HAM. Using our results, network reliability and generalization capability can be estimated when both the interconnection faults and the number of error bits in the probe vectors are taken into account.

Original languageEnglish
Pages (from-to)969-980
Number of pages12
JournalIEEE Transactions on Neural Networks
Volume3
Issue number6
DOIs
Publication statusPublished - 1992 Nov

Fingerprint

Associative Memory
Interconnection
Data storage equipment
Short circuit currents
Fault
Network Reliability
Neurons
Neuron
Networks (circuits)
Error correction
Masks
Error Correction
Mask
Updating
Probe
Update
Radius

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Cite this

@article{7b0cf8bf1c324a46ada13b032bf7b157,
title = "Characteristics of Hebbian-Type Associative Memories Having Faulty Interconnections",
abstract = "The performance of Hebbian-type associative memories (HAM's) in the presence of faulty interconnections is examined and equations for predicting network reliability are developed. The interconnection faults considered are the equivalents of open-circuit and short-circuit synaptic interconnections (analogously, opaque or clear weight mask elements in optical implementations). Our results show that a network with open-circuit interconnection faults has a higher probability of direct convergence, Pdc, than a network with short-circuit interconnection faults when the fraction of failed interconnections, p, is small and the short-circuit signal, G, is large. Our results are also extended to the case where network attraction radius is considered. During the analysis, a HAM is assumed to have a high probability of correct recall; i.e., memory storage is within its capacity. The individual neuron updating in an asynchronous network is assumed to occur in sequential order. Using these assumptions, it was found that the expected numbers of neurons having b. b - 1, b - 2.….1 input error bits in their state update are equal. Because of the capability of error correction, an asynchronous HAM is also found to have a higher Pdc than a synchronous HAM. Using our results, network reliability and generalization capability can be estimated when both the interconnection faults and the number of error bits in the probe vectors are taken into account.",
author = "Chung, {Pau Choo} and Krile, {Thomas F.}",
year = "1992",
month = "11",
doi = "10.1109/72.165598",
language = "English",
volume = "3",
pages = "969--980",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "6",

}

Characteristics of Hebbian-Type Associative Memories Having Faulty Interconnections. / Chung, Pau Choo; Krile, Thomas F.

In: IEEE Transactions on Neural Networks, Vol. 3, No. 6, 11.1992, p. 969-980.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Characteristics of Hebbian-Type Associative Memories Having Faulty Interconnections

AU - Chung, Pau Choo

AU - Krile, Thomas F.

PY - 1992/11

Y1 - 1992/11

N2 - The performance of Hebbian-type associative memories (HAM's) in the presence of faulty interconnections is examined and equations for predicting network reliability are developed. The interconnection faults considered are the equivalents of open-circuit and short-circuit synaptic interconnections (analogously, opaque or clear weight mask elements in optical implementations). Our results show that a network with open-circuit interconnection faults has a higher probability of direct convergence, Pdc, than a network with short-circuit interconnection faults when the fraction of failed interconnections, p, is small and the short-circuit signal, G, is large. Our results are also extended to the case where network attraction radius is considered. During the analysis, a HAM is assumed to have a high probability of correct recall; i.e., memory storage is within its capacity. The individual neuron updating in an asynchronous network is assumed to occur in sequential order. Using these assumptions, it was found that the expected numbers of neurons having b. b - 1, b - 2.….1 input error bits in their state update are equal. Because of the capability of error correction, an asynchronous HAM is also found to have a higher Pdc than a synchronous HAM. Using our results, network reliability and generalization capability can be estimated when both the interconnection faults and the number of error bits in the probe vectors are taken into account.

AB - The performance of Hebbian-type associative memories (HAM's) in the presence of faulty interconnections is examined and equations for predicting network reliability are developed. The interconnection faults considered are the equivalents of open-circuit and short-circuit synaptic interconnections (analogously, opaque or clear weight mask elements in optical implementations). Our results show that a network with open-circuit interconnection faults has a higher probability of direct convergence, Pdc, than a network with short-circuit interconnection faults when the fraction of failed interconnections, p, is small and the short-circuit signal, G, is large. Our results are also extended to the case where network attraction radius is considered. During the analysis, a HAM is assumed to have a high probability of correct recall; i.e., memory storage is within its capacity. The individual neuron updating in an asynchronous network is assumed to occur in sequential order. Using these assumptions, it was found that the expected numbers of neurons having b. b - 1, b - 2.….1 input error bits in their state update are equal. Because of the capability of error correction, an asynchronous HAM is also found to have a higher Pdc than a synchronous HAM. Using our results, network reliability and generalization capability can be estimated when both the interconnection faults and the number of error bits in the probe vectors are taken into account.

UR - http://www.scopus.com/inward/record.url?scp=0026954429&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026954429&partnerID=8YFLogxK

U2 - 10.1109/72.165598

DO - 10.1109/72.165598

M3 - Article

AN - SCOPUS:0026954429

VL - 3

SP - 969

EP - 980

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 6

ER -