Abstract | ||
---|---|---|
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 0or= 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. |
Year | DOI | Venue |
---|---|---|
1992 | 10.1109/34.107015 | Pattern Analysis and Machine Intelligence, IEEE Transactions |
Keywords | Field | DocType |
neural nets,protocols,computing capabilities,decision errors,error tolerance,exhaustive error protocol,formal McCulloch-Pitts neurons,neural nets,random error protocol | Boolean function,Content-addressable memory,Computer science,Theoretical computer science,Artificial intelligence,Artificial neural network,Reliability theory,Computation,Pattern recognition,Error tolerance,Arithmetic,Fault tolerance,Large deviations theory | Journal |
Volume | Issue | ISSN |
14 | 1 | 0162-8828 |
Citations | PageRank | References |
3 | 1.70 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Santosh S. Venkatesh | 1 | 381 | 71.80 |
Demetri Psaltis | 2 | 431 | 209.24 |