Title :
Neuro-fuzzy logic
Author :
Glorennec, Pierre-Yves
Author_Institution :
Inst. Nat. des Sci. Appliques, Rennes, France
Abstract :
Neural VLSI devices are now available and it would be interesting to use them for logical operations. We show that, in the Lukasiewicz logic, it is possible to use an artificial neuron to implement four basic logical operators (conjunction, disjunction, implication and negation). A new operator, AND-OR, is introduced with the same formalism. Finally, a smoothed form of the logical operators make it possible for their implementation on actual hardware
Keywords :
fuzzy logic; fuzzy neural nets; generalisation (artificial intelligence); inference mechanisms; learning (artificial intelligence); neural nets; uncertainty handling; AND-OR operator; Lukasiewicz logic; artificial neuron; conjunction; disjunction; fuzzy inference; generalisation; neuro-fuzzy logic; Boolean functions; Fuzzy logic; Hardware; Logic devices; Neurons; Open wireless architecture; Smoothing methods; Very large scale integration;
Conference_Titel :
Fuzzy Systems, 1996., Proceedings of the Fifth IEEE International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-3645-3
DOI :
10.1109/FUZZY.1996.552298
