Title :
Characterizing numbers of n-variable logic functions implementable by threshold Adalines with integral weights between -2 and 2
Author_Institution :
Dept. of Electr. Eng., New Brunswick Univ., Fredericton, NB, Canada
fDate :
27 Jun-2 Jul 1994
Abstract :
The threshold Adaline (Adaptive Linear Element) is the basic processing unit of many neural networks. The characterizing numbers of logic functions which are realizable by a single threshold Adaline with integral weights between -2 and 2 are examined. In so doing, a realization test and procedure are developed as well as a closed-form expression for the number of such logic functions
Keywords :
functions; neural nets; polynomials; threshold logic; Adaptive Linear Element; closed-form expression; integral weights; n-variable logic functions; neural networks; polynomials; single threshold Adaline; threshold Adalines; Hypercubes; Input variables; Logic functions; Logic testing; Polynomials;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374285
