Answers are grounded in this paper and cite their sources.
A method of network synthesis for general combinational functions that uses a number of fixed threshold logic units not greatly in excess of the theoretical minimum is described. It can be used with adaptive logic in which case a minority of the interconnections are simply adapted once according to the rule originally suggested by Hebb. This network on its own has no capacity for ``generalization,'' and if used for pattern recognition must therefore be operated in conjunction with a suitable property filter, such as that of the previous paper.[1] In this case the present network could perform as a trainable ``categorizer.''
No takes yet. Share an insight, caveat, or question.
David Smith (1968) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: