A novel high-order associative memory system via discrete Taylor series

This paper proposes a novel high-order associative memory system (AMS) based on the discrete Taylor series (DTS). The mathematical foundation for the new AMS scheme is derived, three training algorithms are proposed, and the convergence of learning is proved. The DTS-AMS thus developed is capable of implementing error-free approximation to multivariable polynomial functions of arbitrary order. Compared with cerebellar model articulation controllers and radial basis function neural networks, it provides higher learning precision and less memory request. Furthermore, it offers less training computation and faster convergence rate than that attainable by multilayer perceptron. Numerical simulations show that the proposed DTS-AMS is effective in higher order function approximation and has potential in practical applications.

[1]  J. L. Schiano,et al.  Hash-coding in CMAC neural networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[2]  Ning-Shou Xu,et al.  A novel associative memory system based on sharp-angled hat spline functions , 1996, 1996 IEEE International Conference on Systems, Man and Cybernetics. Information Intelligence and Systems (Cat. No.96CH35929).

[3]  Neil E. Cotter,et al.  A pulsed neural network capable of universal approximation , 1992, IEEE Trans. Neural Networks.

[4]  W. T. Miller,et al.  CMAC: an associative neural network alternative to backpropagation , 1990, Proc. IEEE.

[5]  James S. Albus,et al.  New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC)1 , 1975 .

[6]  C. S. Berger.  Linear splines with adaptive mesh sizes for modelling nonlinear dynamic systems , 1994 .

[7]  Chun-Shin Lin,et al.  Learning convergence of CMAC technique , 1997, IEEE Trans. Neural Networks.

[8]  L. G. Kraft,et al.  Comparison of convergence properties of CMAC neural networks and traditional adaptive controllers , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[9]  Chun-Shin Lin,et al.  Integration of CMAC technique and weighted regression for efficient learning and output differentiability , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[10]  Antonio Artés-Rodríguez,et al.  Fourier analysis of the generalized CMAC neural network , 1998, Neural Networks.

[11]  David E. Thompson,et al.  Neighborhood sequential and random training techniques for CMAC , 1995, IEEE Trans. Neural Networks.

[12]  Enis Ersü,et al.  Learning control with interpolating memories―general ideas, design lay-out, theoretical approaches and practical applications , 1992 .

[13]  Aníbal R. Figueiras-Vidal,et al.  Generalizing CMAC architecture and training , 1998, IEEE Trans. Neural Networks.

[14]  Chun-Shin Lin,et al.  Integration of CMAC and radial basis function techniques , 1995, 1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century.

[15]  A. Sideris,et al.  Learning convergence in the cerebellar model articulation controller , 1992, IEEE Trans. Neural Networks.

[16]  D.A. Handelman,et al.  Theory and development of higher-order CMAC neural networks , 1992, IEEE Control Systems.

[17]  W. W. Bell.  Matrices for scientists and engineers , 1975 .

[18]  Hong Zhang,et al.  A New Content-Addressing Mechanism of CMAC-Type Associative Memory Systems for Reducing the Required Memory Size , 1996 .

[19]  M. Brown,et al.  Least mean square learning in associative memory networks , 1992, Proceedings of the 1992 IEEE International Symposium on Intelligent Control.