✦ LIBER ✦

Stability analysis of neural net controllers using fuzzy neural networks

✍ Scribed by Thomas Feuring; James J. Buckley; Wolfram-M. Lippe; Andreas Tenhagen

Publisher: Elsevier Science
Year: 1999
Tongue: English
Weight: 810 KB
Volume: 101
Category: Article
ISSN: 0165-0114
DOI: 10.1016/s0165-0114(98)00172-9

No coin nor oath required. For personal study only.

✦ Synopsis

Neural networks can only be trained with a crisp and finite data set. Therefore, the approximation quality of a trained network is hard to verify. So, a common way in proving stability of a trained neural net controller is to demonstrate the existence of a Lyapunov function. In this article we propose a new method how stability of a neural net controller, used as a closedqoop feedback controller, can be proven. Instead of finding a Lyapunov function, conditions for a fuzzy training set are developed. If a fuzzy neural net is trained using this training set special properties of fuzzy neural nets can be used for estimating the generalization error. After defuzzification of the fuzzy net finite stability of the process can be concluded.

📜 SIMILAR VOLUMES

Fuzzy regression analysis using neural n

Fuzzy regression analysis using neural networks

✍ Hisao Ishibuchi; Hideo Tanaka 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 605 KB

Application of neural networks to fuzzy

Application of neural networks to fuzzy control

✍ Faouzi Bouslama; Akira Ichikawa 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 510 KB

This paper gives a possible application of neural networks to fuzzy control. In fuzzy control a set of linguistic rules are given and by specifying a method or fuzzy reasoning and defit--ification an input-output relation is obtained. Fuzz), controllers thus obtained are usuallj, irregTdar, and are

Implementing fuzzy logic controllers usi

Implementing fuzzy logic controllers using a neural network framework

✍ Ronald R. Yager 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 701 KB

Stability analysis of uncertain fuzzy Ho

Stability analysis of uncertain fuzzy Hopfield neural networks with time delays

✍ M. Syed Ali; P. Balasubramaniam 📂 Article 📅 2009 🏛 Elsevier Science 🌐 English ⚖ 300 KB

In this paper, the global stability problem of uncertain Takagi-Sugeno (T-S) fuzzy Hopfield neural networks with time delays (TSFHNNs) is considered. A novel LMI-based stability criterion is obtained by using Lyapunov functional theory to guarantee the asymptotic stability of TSFHNNs. Here, we choos

A model reference control structure usin

A model reference control structure using a fuzzy neural network

✍ Yie-Chien Chen; Ching-Cheng Teng 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 981 KB

Stability analysis of delayed cellular n

Stability analysis of delayed cellular neural networks

✍ Jinde Cao; Dongming Zhou 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 74 KB

In this paper, the problems of stability in a class of delayed cellular neural networks (DCNN) are studied; some new stability criteria are obtained by using the Lyapunov functional method and some analysis techniques. These criteria can be used to design globally stable networks and thus have impor