Universal approximation of a class of interval type-2 fuzzy neural networks in nonlinear identification

DOI10.1155/2013/136214MaRDI QIDQ888663zbMATH OpenOpenAlexWikidataFDO

Authors Oscar Castillo, Juan R. Castro, Patricia Melin, Antonio Rodriguez-Diaz

Publication date 2 November 2015

Published in Advances in Fuzzy Systems (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1155/2013/136214

Mathematics Subject Classification ID

Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Neural nets and related approaches to inference from stochastic processes (62M45) Learning and adaptive systems in artificial intelligence (68T05)

Review text

Summary: Neural networks (NNs), type-1 fuzzy logic systems (T1FLSs), and interval type-2 fuzzy logic systems (IT2FLSs) have been shown to be universal approximators, which means that they can approximate any nonlinear continuous function. Recent research shows that embedding an IT2FLS on an NN can be very effective for a wide number of nonlinear complex systems, especially when handling imperfect or incomplete information. In this paper we show, based on the Stone-Weierstrass theorem, that an interval type-2 fuzzy neural network (IT2FNN) is a universal approximator, which uses a set of rules and interval type-2 membership functions (IT2MFs) for this purpose. Simulation results of nonlinear function identification using the IT2FNN for one and three variables and for the Mackey-Glass chaotic time series prediction are presented to illustrate the concept of universal approximation.

Recommendations

• Advances in Neural Networks – ISNN 2005
• Capability of universal approximations of feedforward regular fuzzy neural networks in K-integral norm
• A hybrid learning algorithm for a class of interval type-2 fuzzy neural networks
• Universal approximations of continuous fuzzy-valued functions by multi-layer regular fuzzy neural networks
• A type-2 fuzzy wavelet neural network for system identification and control
• Interval type-2 recurrent fuzzy neural system for nonlinear systems control using stable simultaneous perturbation stochastic approximation algorithm
• Universal approximation of fuzzy functions by polygonal fuzzy neural networks

Cites work

• A hybrid learning algorithm for a class of interval type-2 fuzzy neural networks
• Can fuzzy neural nets approximate continuous fuzzy functions?
• Fuzzy sets
• Fuzzy systems as universal approximators
• Multilayer feedforward networks are universal approximators
• Oscillation and chaos in physiological control systems
• Sugeno type controllers are universal controllers
• Universal approximation by hierarchical fuzzy system with constraints on the fuzzy rule
• Universal fuzzy controllers

Cited in

(6)

• A type-2 fuzzy wavelet neural network for system identification and control
• Improved adaptive sliding mode control for a class of uncertain nonlinear systems subjected to input nonlinearity via fuzzy neural networks
• Genetic algorithm and particle swarm optimization based cascade interval type 2 fuzzy PD controller for rotary inverted pendulum system
• Nonstationary fuzzy neural network based on fcmnet clustering and a modified CG method with Armijo-type rule
• Refined fault tolerant tracking control of fixed-wing UAVs via fractional calculus and interval type-2 fuzzy neural network under event-triggered communication
• Novel Levenberg-Marquardt based learning algorithm for unmanned aerial vehicles

This page was built for publication: Universal approximation of a class of interval type-2 fuzzy neural networks in nonlinear identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q888663)