This Article 
 Bibliographic References 
 Add to: 
The Analysis of the Faulty Behavior of Synchronous Neural Networks
December 1991 (vol. 40 no. 12)
pp. 1424-1429

A means for analyzing the faulty behavior of neural networks is presented. Using an analogy between statistical physics and neural networks, a method for assessing the performance of a synchronous neural network model in the presence of faults is developed. Analytical predictions are computed using the statistical physics analogy and compared with the simulated behavior for two neuron models. An example of the analytical technique applied to an autoassociative memory is described.

[1] B.W. Johnson,Design and Analysis of Fault Tolerant Digital Systems, Addison-Wesley, Reading, Mass., 1989.
[2] J. J. Hopfield, "Neural networks and physical systems with emergent collective computational abilities,"Proc. Nat. Acad. Sci. USA., vol. 79, pp. 2554-2558, Apr. 1982.
[3] J. A. G. Nijhuis and L. Spaanenburg, "Fault tolerance of neural associative memories,"IEE Proc., vol. 136, pt. E, no. 5, pp. 389-394, Sept. 1989.
[4] L. A. Belfore and B. W. Johnson, "The fault tolerance of neural networks,"Int. J. Neural Networks Res. and Appl., vol. 1, no. 1, pp. 24-41, Jan. 1989.
[5] G. E. Hinton and T. J. Sejnowski, "Learning and relearning in Boltzmann machines," inPARALLEL DISTRIBUTED PROCESSING: Explorations in the Microstructure of Cognition, Vol. 1: Foundations, pp. 282-317.
[6] T. Petsche and B. W. Dickinson, "Trellis codes, receptive fields, and fault tolerant, self-repairing neural networks,"IEEE Trans. Neural Networks, vol. 1, pp. 154-166, June 1990.
[7] J. L. McClelland, "Resource requirements of standard and programmable nets," inPARALLEL DISTRIBUTED PROCESSING: Explorations in the Microstructure of Cognition, Vol. 1: Foundations, pp. 461-487.
[8] H. Sompolinsky, "Neural networks with nonlinear synapses and a static noise,"Phys. Rev. A, vol. 34, no. 3, pp. 2571-2574, Sept. 1986.
[9] M. Stevenson, R. Winter, and B. Widrow, "Sensitivity of feedforward neural networks to weight errors,"IEEE Trans. Neural Networks, vol. 1, no. 1, pp. 71-80, Mar. 1990.
[10] L. A. Belfore, II, B. W. Johnson, and J. H. Aylor, "Modeling of fault tolerance in neural networks," inProc. Fifteenth Annu. Conf. IEEE Industrial Electron. Soc., Philadelphia, PA, Nov. 6-10, 1989, pp. 783-758.
[11] W. A. Little, "The existence of persistent states in the brain,"Mathemat. Biosci., vol. 19, pp. 101-120, 1974.
[12] L. A. Belfore, "Modeling the performance of faulty neural networks," Ph.D. dissertation, Univ. of Virginia, Charlottesville, VA, Jan. 1990.
[13] A. Paz,Introduction to Probabilistic Automata. New York: Academic, 1971.

Index Terms:
performance assessment; analytical predictions; faulty behavior; synchronous neural networks; statistical physics; simulated behavior; content-addressable storage; fault tolerant computing; neural nets.
L.A. Belfore, II, B.W. Johnson, "The Analysis of the Faulty Behavior of Synchronous Neural Networks," IEEE Transactions on Computers, vol. 40, no. 12, pp. 1424-1429, Dec. 1991, doi:10.1109/12.106228
Usage of this product signifies your acceptance of the Terms of Use.