Issue No. 01 - January (1992 vol. 14)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.107015
<p>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.</p>
neural nets; computing capabilities; formal McCulloch-Pitts neurons; decision errors; error tolerance; random error protocol; exhaustive error protocol; neural nets; protocols
D. Psaltis and S. Venkatesh, "On Reliable Computation With Formal Neurons," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 14, no. , pp. 87-91, 1992.