Title :
On the equivalence of neural networks and fuzzy expert systems
Author :
Buckley, James J. ; Hayashi, Yoichi ; Czogala, Ernest
Author_Institution :
Dept. of Maths., Alabama Univ., Birmingham, AL, USA
Abstract :
It is proven that any continuous, layered, feedforward neural net can be approximated to any degree of accuracy by a (discrete) fuzzy expert system, and that any continuous, discrete, fuzzy expert system with one block of rules may be approximated to any degree of accuracy by a three layered, feedforward neural net. The second result may be generalized to multiple blocks of rules by considering total (discrete) input and total (discrete) output from the fuzzy expert system. It is concluded that fuzzy expert systems and neural nets can both approximate functions (mappings, systems)
Keywords :
expert systems; feedforward neural nets; fuzzy logic; discrete fuzzy expert systems; equivalence; feedforward neural net; fuzzy expert systems; neural networks; Computer science; Equations; Feedforward neural networks; Fuzzy sets; Hybrid intelligent systems; Logistics; Mathematics; Neural networks; Neurons; Virtual manufacturing;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.226907
