The equivalence between fuzzy logic systems and feedforward neural networks

Authors
Citation
Hx. Li et Clp. Chen, The equivalence between fuzzy logic systems and feedforward neural networks, IEEE NEURAL, 11(2), 2000, pp. 356-365
Citations number
16
Categorie Soggetti
AI Robotics and Automatic Control
Journal title
IEEE TRANSACTIONS ON NEURAL NETWORKS
ISSN journal
10459227 → ACNP
Volume
11
Issue
2
Year of publication
2000
Pages
356 - 365
Database
ISI
SICI code
1045-9227(200003)11:2<356:TEBFLS>2.0.ZU;2-Q
Abstract
Abr;This paper demonstrates that fuzzy logic systems and feedforward neural networks are equivalent in essence. First, we introduce the concept of int erpolation representations of fuzzy logic systems and several important con clusions. We then define mathematical model for rectangular wave neural net works and nonlinear neural networks. With this definition, we prove that no nlinear neural networks can be represented by rectangular wave neural netwo rks. Based on this result, we prove the equivalence between fuzzy logic sys tems and feedforward neural networks, This result provides us a very useful guideline when we perform theoretical research and applications on fuzzy l ogic systems, neural networks, or neuro-fuzzy systems.