Type-2 fuzzy activation function for multilayer feedforward neural networks

This paper presents a new type-2 fuzzy based activation function for multilayer feedforward neural networks. Instead of other activation functions, the proposed approach uses a type-2 fuzzy set to accelerate backpropagation learning and reduce number of neurons in the complex net. Furthermore, the type-2 fuzzy based activation function provides to minimize the effects of uncertainties on the neural network. Performance of the type-2 fuzzy activation function is demonstrated by exor and speed estimation of induction motor problems in simulations. The comparison among the proposed activation function and commonly used activation functions shows accelerated convergence and eliminated uncertainties with the proposed method. The simulation results showed that the proposed method is more suitable to complex systems.

[1]  E. Mizutani,et al.  Neuro-Fuzzy and Soft Computing-A Computational Approach to Learning and Machine Intelligence [Book Review] , 1997, IEEE Transactions on Automatic Control.

[2]  Bin-Da Liu,et al.  An adaptive activation function for multilayer feedforward neural networks , 2002, 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering. TENCOM '02. Proceedings..

[3]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1993 .

[4]  Jerry M. Mendel,et al.  Type-2 fuzzy logic systems , 1999, IEEE Trans. Fuzzy Syst..

[5]  Danilo P. Mandic,et al.  On sensitivity of neural adaptive filters with respect to the slope parameter of a neuron activation function , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Ji-Yoon Yoo,et al.  Speed-sensorless vector control of an induction motor using neural network speed estimation , 2001, IEEE Trans. Ind. Electron..

[7]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[8]  Bimal K. Bose,et al.  Modern Power Electronics and AC Drives , 2001 .

[9]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[10]  Antonio J. Serrano,et al.  A low-complexity fuzzy activation function for artificial neural networks , 2003, IEEE Trans. Neural Networks.

[11]  Joarder Kamruzzaman,et al.  A note on activation function in multilayer feedforward learning , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[12]  A. G. Parlos,et al.  NEURAL STATE FILTERING FOR ADAPTIVE INDUCTION MOTOR SPEED ESTIMATION , 2003 .

[13]  N. Suha Bayindir,et al.  Speed estimation of an induction motor using Elman neural network , 2003, Neurocomputing.

[14]  Erhan Akin,et al.  A New Fuzzy Controller Based on an Integrator Algorithm for Stator Flux Estimation in Induction Motors , 2002 .

[15]  Shyh-Jier Huang,et al.  Sensorless speed identification of vector—controlled induction drives via neural network based estimation , 1998 .