Title :
Algebraic properties of a learning multiple-valued logic network
Author :
Tang, Zheng ; Ishizuka, Okihiko ; Cao, Qi-Xin ; Matsumoto, Hiroki
Author_Institution :
Fac. of Eng., Miyazaki Univ., Japan
Abstract :
A simple arithmetic piecewise linear operator that can be used as a basic element to construct a large multiple-valued network is defined. The algebra is proved to be a functionally complete set and capable of constructing any multiple-valued logic functions. The layered piecewise linear node networks provide a natural and general architecture for backpropagation, thus making a learning multiple-valued logic network possible
Keywords :
backpropagation; learning systems; many-valued logics; piecewise-linear techniques; backpropagation; learning; multiple-valued logic network; multiple-valued network; piecewise linear operator; Algebra; Arithmetic; CMOS logic circuits; Circuit synthesis; Ear; Image processing; Logic functions; Network synthesis; Piecewise linear techniques; Speech recognition;
Conference_Titel :
Multiple-Valued Logic, 1993., Proceedings of The Twenty-Third International Symposium on
Conference_Location :
Sacramento, CA
Print_ISBN :
0-8186-3350-6
DOI :
10.1109/ISMVL.1993.289560
