Title :
Stability and Admissibility of Adaptive Threshold Logic Convergence
Author :
Gaines, B.R. ; Witten, I.H.
Author_Institution :
Man-Machine Systems Laboratory, Department of Electrical Engineering, University of Essex, Colchester, Essex.
Abstract :
It is shown that an adaptive threshold logic element (ATLE) whose weight vector is perturbed reconverges without error provided its threshold is large compared with the perturbation. This result is generalized to a criterion of convergence, based on admissibility, for the nonseparable case. It is shown that conventional ATLE´s cannot cope with nonseparability even according to this very weak criterion.
Keywords :
Adaptive equalizers; Adaptive systems; Convergence; Logic; Machine learning; Man machine systems; Pattern recognition; Stability; Adaptive threshold logic; convergence; nonseparability; perceptron; threshold;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/TC.1977.5009280