A neural fuzzy system with linguistic teaching signals

• Published in: IEEE transactions on fuzzy systems Vol. 3; no. 2; pp. 169 - 189
• Main Authors: LIN, C.-T, LU, Y.-C
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.05.1995; Institute of Electrical and Electronics Engineers
• Subjects: Adaptive control; Adaptive systems; Applied sciences; Artificial intelligence; Computer science; control theory; systems; Connectionism. Neural networks; Control systems; Education; Exact sciences and technology; Fuzzy control; Fuzzy logic; Fuzzy systems; Hybrid intelligent systems; Learning and adaptive systems; Neural networks; Programmable control; Speech and sound recognition and synthesis. Linguistics; Learning; Linguistics; Inference; Fuzzy system; Neural network; Simulation
• ISSN: 1063-6706
• DOI: 10.1109/91.388172

A neural fuzzy system learning with linguistic teaching signals is proposed. This system is able to process and learn numerical information as well as linguistic information. It can be used either as an adaptive fuzzy expert system or as an adaptive fuzzy controller. First, we propose a five-layered neural network for the connectionist realization of a fuzzy inference system. The connectionist structure can house fuzzy logic rules and membership functions for fuzzy inference. We use /spl alpha/-level sets of fuzzy numbers to represent linguistic information. The inputs, outputs, and weights of the proposed network can be fuzzy numbers of any shape. Furthermore, they can be hybrid of fuzzy numbers and numerical numbers through the use of fuzzy singletons. Based on interval arithmetics, two kinds of learning schemes are developed for the proposed system: fuzzy supervised learning and fuzzy reinforcement learning. Simulation results are presented to illustrate the performance and applicability of the proposed system.< >