Title :
An Approach to Optimum Tolerance Adaptive Threshold Elements
Author :
Colussi, S.P. ; Pallottino, G.V.
Author_Institution :
IEEE
fDate :
7/1/1968 12:00:00 AM
Abstract :
Abstract—A definition of the tolerance for the weights of adaptive threshold elements is given which is more relevant to the characteristics of real adaptive components. A learning procedure is then proposed, which employs a sequence of different and increasing values of dead zone. This procedure achieves the determination of the set of maximum tolerance weights and its soundness is shown by systematic tests performed by simulation on an IBM 7094 digital computer on all the binary functions of 5 variables.
Keywords :
Index terms—Adaptive systems, adaptive threshold element, learning procedures, learning time, optimum tolerance learning.; Acoustic testing; Adaptive algorithm; Adaptive systems; Computational modeling; Computer simulation; Gain; Laboratories; Linearity; Performance evaluation; System testing; Index terms—Adaptive systems, adaptive threshold element, learning procedures, learning time, optimum tolerance learning.;
Journal_Title :
Computers, IEEE Transactions on
DOI :
10.1109/TC.1968.227418
