Abstract
In this paper, the McCulloch-Pitts model of a neuron is extended to a more general model which allows the activity of a neuron to be a “fuzzy” rather than an “all-or-none” process. The generalized model is called a fuzzy neuron. Some basic properties of fuzzy neural networks as well as their applications to the synthesis of fuzzy automata are investigated. It is shown that any n-state minimal fuzzy automatan can be realized by a network of m fuzzy neurons, where ⌈log2n⌉<m<2n. Examples are given to illustrate the procedure. As an example of application, a realization of fuzzy language recognizer using a fuzzy neural network is presented. The techniques described in this paper may be of use in the study of neural networks as well as in language, pattern recognition, and learning.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call