Showing papers on "Neuro-fuzzy published in 1974"

Numerical taxonomy with fuzzy sets

Abstract: A recently developed fuzzy clustering technique is utilized to analyze the substructure of a well known set of 4-dimensional botanical data. A solution obtained without prior knowledge of labelled pattern structure is offered in support of our contention that the technique proposed affords a comparatively reliable criterion for a posteriori evaluation of cluster validity.

Concept representation in natural and artificial languages: Axioms, extensions and applications for fuzzy sets

Abstract: This paper reports research related to mathematics, philosophy, computer science and linguistics. It gives a system of axioms for a relatively simple form of fuzzy set theory, and uses these axioms to consider the accuracy of representing concepts in various ways by fuzzy sets. By-products of this approach include a number of new operations and laws for fuzzy sets, parallel to those for ordinary sets, and a demonstration that all the basic operations are intrinsically determined. In addition, the paper explores both hierarchical and algorithmic extensions of fuzzy sets, and then applications to problems in natural language semantics and combinatorics. Finally, the paper returns to the problem of representing concepts, and discusses some implications for artificial intelligence.

Fuzzy Sets and Neural Networks

Abstract: It is possible that a better model for the behavior of a nerve cell may be provided by what might be called a fuzzy neuron, which is a generalization of the McCulloch-Pitts model. The concept of a fuzzy neuron employs some of the concepts and techniques of the theory of fuzzy sets which was introduced by Zadeh [2, 3] and applied to the theory of automaton by Wee and Fu [6], Tanaka et al. [7], Santo [8] and others. In effect, the introduction of fuzziness into the model of a neuron makes it better adapted to the study of the behavior of systems which are imprecisely defined by virtue of their high degree of complexity. Many of the biological systems, economic systems, urban systems and more generally, large-scale systems fall into this category. In the nearly three decades since its publication, the pioneering work of McCulloch and Pitts [1], has had a profound influence on the development of the theory of neural nets, in addition to stimulating much of the early work in automata theory and regula...

Fuzzy systems and artificial intelligence

Abstract: Many concepts of problem solving theory are better understood in an abstract algebraic framework which also applies in automata theory Because many systems of practical interest fall outside the scope of linear theory, it is desirable to enlarge as much as possible the class of systems for which a complete structure theory is available The fuzzy system approach is presented as a basis for the design of systems far superior in artificial intelligence to those we can conceive today The concepts of controllability, observability and minimality are developed, and conditions for the realization of an input‐output map by such a system are given Several problems, all directly or indirectly related to fuzzification, arise in considering this broader class of systems

Evaluation Model of Humanistic Systems by Fuzzy Multiple Integral and Fuzzy Correlation

Abstract: We have proposed a mathematical model of subjective evaluation on the basis of fuzzy integral. In particular, we have developed the evaluating method of complex systems composed of several subsystems by virtue of fuzzy multiple integral. Furthermore, for the sake of identifying the preference measure, that is fuzzy measure , effectively, we have introduced the fuzzy correlation.