Neural control theory : an overview

In this paper we present a short introduction to the theory of neural control. Universal approximation, on- and off-line learning ability and parallelism of neural networks are the main motivation for their application to modelling and control problems. This has led to several existing neural control strategies. An overview of methods is presented, with emphasis on the foundations of neural optimal control, stability theory and nonlinear system identification using neural networks for modelbased neural control design.

[1]  Richard S. Sutton,et al.  Neuronlike adaptive elements that can solve difficult learning control problems , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[3]  A. Sideris,et al.  A multilayered neural network controller , 1988, IEEE Control Systems Magazine.

[4]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[5]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[6]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[7]  B. Widrow,et al.  Neural networks for self-learning control systems , 1990, IEEE Control Systems Magazine.

[8]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[9]  Shang-Liang Chen,et al.  Orthogonal least squares learning algorithm for radial basis function networks , 1991, IEEE Trans. Neural Networks.

[10]  Marco Saerens,et al.  Neural controller based on back-propagation algorithm , 1991 .

[11]  Daniel Sbarbaro,et al.  Neural Networks for Nonlinear Internal Model Control , 1991 .

[12]  Robert M. Sanner,et al.  Gaussian Networks for Direct Adaptive Control , 1991, 1991 American Control Conference.

[13]  Kumpati S. Narendra,et al.  Gradient methods for the optimization of dynamical systems containing neural networks , 1991, IEEE Trans. Neural Networks.

[14]  R.J. Williams,et al.  Reinforcement learning is direct adaptive optimal control , 1991, IEEE Control Systems.

[15]  Peter J. Gawthrop,et al.  Neural networks for control systems - A survey , 1992, Autom..

[16]  L. Ljung,et al.  Overtraining, Regularization, and Searching for Minimum in Neural Networks , 1992 .

[17]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[18]  Eduardo D. Sontag,et al.  Neural Networks for Control , 1993 .

[19]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[20]  Wolfram Schiffmann,et al.  Adaptive control of dynamic systems by back propagation networks , 1993, Neural Networks.

[21]  Thomas Parisini,et al.  Neural networks for feedback feedforward nonlinear control systems , 1994, IEEE Trans. Neural Networks.

[22]  Patrick van der Smagt.  Minimisation methods for training feedforward neural networks , 1994, Neural Networks.

[23]  Johan A. K. Suykens,et al.  Static and dynamic stabilizing neural controllers, applicable to transition between equilibrium points , 1994, Neural Networks.

[24]  Hugues Bersini,et al.  Comparing RBF and Fuzzy Inference Systems on theoretical and practical basis , 1995 .

[25]  Marco Saerens,et al.  Neurocontrollers based on backpropagation algorithm , 1995 .

[26]  Lennart Ljung,et al.  Nonlinear black-box modeling in system identification: a unified overview , 1995, Autom..

[27]  Hugues Bersini,et al.  A simplification of the backpropagation-through-time algorithm for optimal neurocontrol , 1997, IEEE Trans. Neural Networks.

[28]  E. Yaz.  Linear Matrix Inequalities In System And Control Theory , 1998, Proceedings of the IEEE.