This Article 
 Bibliographic References 
 Add to: 
On Reliable Computation With Formal Neurons
January 1992 (vol. 14 no. 1)
pp. 87-91

The authors investigate the computing capabilities of formal McCulloch-Pitts neurons when errors are permitted in decisions. They assume that m decisions are to be made on a randomly specified m set of points in n space and that an error tolerance of epsilon m decision errors is allowed, with 0>or= epsilon >1/2. The authors are interested in how large an m can be selected such that the neuron makes reliable decisions within the prescribed error tolerance. Formal results for two protocols for error-tolerance-a random error protocol and an exhaustive error protocol-are obtained. The results demonstrate that a formal neuron has a computational capacity that is linear in n and that this rate of capacity growth persists even when errors are tolerated in the decisions.

[1] S.S. Venkatesh, "Linear maps with point rules: Applications to pattern classification and associative memory," Ph.D. thesis, California Inst. Technol., 1986.
[2] S. S. Venkatesh, "Epsilon capacity of neural networks," inNeural Networks for Computing(J. Denker, Ed.). New York: AIP, 1986.
[3] W. W. McCulloch, and W. Pitts, "A logical calculus of the ideas immanent in nervous activity,"Bull. Math. Biophys., vol. 5, pp. 115-133, 1943.
[4] L. Schläfli,Gesammelte Mathematische Abhandlungen I. Basel, Switzerland: Verlag Birkhäuser, pp. 209-212, 1950.
[5] s
[6] J. G. Wendel, "A problem in geometric probability,"Math Scand., vol. 11, pp. 109-111, 1962.
[7] T. M. Cover, "Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition,"Electron. Comput., vol. 14, pp. 326-334, 1965.
[8] Y. S. Abu-Mostafa and J. St. Jacques, "Information capacity of the Hopfield model,"IEEE Trans. Inform. Theory, vol. IT-31, pp. 461-464, 1985.
[9] R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, "The capacity of the Hopfield associative memory,"IEEE Trans. Inform. Theory, vol. IT-33, pp. 461-482, 1987.
[10] J. Komlós and R. Paturi, "Convergence results in an associative memory model,"Neural Networks, vol. 1, no. 3, pp. 239-250, 1988.
[11] C. M. Newman, "Memory capacity in neural network models: rigorous lower bounds,"Neural Networks, vol. 1, no. 3, pp. 233-238, 1988.
[12] P. Baldi and S. S. Venkatesh, "On properties of networks of neuron-like elements," inNeural Information Processing Systems(D. Z. Anderson, Ed.). New York: AIP, 1988.
[13] D. Psaltis and S. S. Venkatesh, "Information storage in fully interconnected networks," inEvolution, Learning and Cognition(Y. C. Lee, Ed.), New York: World Scientific, 1989.
[14] S. S. Venkatesh and D. Psaltis, "Linear and logarithmic capacities in associative neural networks,"IEEE Trans. Inform. Theory, vol. 35, pp. 558-568, 1989.
[15] W. Feller,An Introduction to Probability Theory and its Applications, vol. I. New York: Wiley, 1968.
[16] H. Chernoff, "A measure of asymptotic efficiency for tests of a hypothesis based on the sum of observations,"Ann Math. Stat., vol. 23, pp. 493-507, 1952.
[17] Z. Füredi, "Random polytopes in thed-dimensional cube,"Discrete Comput. Geom., vol. 1, pp. 315-319, 1986.
[18] S. S. Venkatesh, "The science of makingerors," to be published inIEEE Trans. Knowledge Data Eng., Mar. 1992.

Index Terms:
neural nets; computing capabilities; formal McCulloch-Pitts neurons; decision errors; error tolerance; random error protocol; exhaustive error protocol; neural nets; protocols
S.S. Venkatesh, D. Psaltis, "On Reliable Computation With Formal Neurons," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 1, pp. 87-91, Jan. 1992, doi:10.1109/34.107015
Usage of this product signifies your acceptance of the Terms of Use.