Learning continuous trajectories in recurrent neural networks with time-dependent weights

This paper is concerned with a general learning (with arbitrary criterion and state-dependent constraints) of continuous trajectories by means of recurrent neural networks with time-varying weights. The learning process is transformed into an optimal control framework, where the weights to be found are treated as controls. A new learning algorithm based on a variational formulation of Pontryagin's maximum principle is proposed. This algorithm is shown to converge, under reasonable conditions, to an optimal solution. The neural networks with time-dependent weights make it possible to efficiently find an admissible solution (i.e., initial weights satisfying state constraints) which then serves as an initial guess to carry out a proper minimization of a given criterion. The proposed methodology may be directly applicable to both classification of temporal sequences and to optimal tracking of nonlinear dynamic systems. Numerical examples are also given which demonstrate the efficiency of the approach presented.

[1]  A. Ioffe,et al.  Theory of extremal problems , 1979 .

[2]  B. Widrow,et al.  The truck backer-upper: an example of self-learning in neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[3]  DeLiang Wang,et al.  On Temporal Generalization of Simple Recurrent Networks , 1996, Neural Networks.

[4]  Visakan Kadirkamanathan,et al.  Dynamic structure neural networks for stable adaptive control of nonlinear systems , 1996, IEEE Trans. Neural Networks.

[5]  N. Toomarian.  Adjoint operators and non adiabatic algorithms in neural networks , 1991 .

[6]  F.-C. Chen,et al.  Back-propagation neural networks for nonlinear self-tuning adaptive control , 1990, IEEE Control Systems Magazine.

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

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

[9]  Emanuel Marom,et al.  Efficient Training of Recurrent Neural Network with Time Delays , 1997, Neural Networks.

[10]  Hideaki Sakai,et al.  A nonlinear regulator design in the presence of system uncertainties using multilayered neural network , 1991, IEEE Trans. Neural Networks.

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

[12]  Miroslaw Galicki,et al.  The Planning of Robotic Optimal Motions in the Presence of Obstacles , 1998, Int. J. Robotics Res..

[13]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[14]  Kwang Y. Lee,et al.  An optimal tracking neuro-controller for nonlinear dynamic systems , 1996, IEEE Trans. Neural Networks.

[15]  Barak A. Pearlmutter.  Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[16]  Kwang Y. Lee,et al.  Diagonal recurrent neural networks for dynamic systems control , 1995, IEEE Trans. Neural Networks.

[17]  Wulfram Gerstner,et al.  Spiking neurons , 1999 .

[18]  Derrick H. Nguyen,et al.  Neural networks for self-learning control systems , 1990 .

[19]  Nader Sadegh,et al.  A perceptron network for functional identification and control of nonlinear systems , 1993, IEEE Trans. Neural Networks.

[20]  H. Kabre,et al.  Robustness of a chaotic modal neural network applied to audio-visual speech recognition , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[21]  D Lehmann,et al.  Instantaneous frequency maps, dipole models and potential distributions of pattern reversal-evoked potential fields for correct recognition of stimulated hemiretinae. , 1996, Electroencephalography and clinical neurophysiology.

[22]  A. Patrikar,et al.  Nonlinear system identification and adaptive control using polynomial networks , 1996 .

[23]  Jacques Ludik,et al.  A Multilayer Real-Time Recurrent Learning Algorithm for Improved Convergence , 1997, ICANN.

[24]  Marios M. Polycarpou,et al.  High-order neural network structures for identification of dynamical systems , 1995, IEEE Trans. Neural Networks.

[25]  Derrick H. Nguyen,et al.  Truck backer-upper: an example of self-learning in neural networks , 1990, Defense, Security, and Sensing.

[26]  R. P. Fedorenko.  Approximate solution of some optimal control problems , 1964 .

[27]  Pierre Baldi,et al.  Gradient descent learning algorithm overview: a general dynamical systems perspective , 1995, IEEE Trans. Neural Networks.

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

[29]  Herbert Witte,et al.  Structure optimization of neural networks with the A*-algorithm , 1997, IEEE Trans. Neural Networks.

[30]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[31]  Anthony J. Robinson,et al.  Static and Dynamic Error Propagation Networks with Application to Speech Coding , 1987, NIPS.

[32]  Yuichi Nakamura,et al.  Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[33]  L. A. Li︠u︡sternik,et al.  Elements of Functional Analysis , 1962 .

[34]  Peter H. Meckl,et al.  An analytical comparison of a neural network and a model-based adaptive controller , 1993, IEEE Trans. Neural Networks.

[35]  A. Atiya,et al.  Application of neural networks to the problem of forecasting the flow of the River Nile , 1997, Neural Networks for Signal Processing VII. Proceedings of the 1997 IEEE Signal Processing Society Workshop.

[36]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[37]  J. Barhen,et al.  Adjoint-operators and non-adiabatic learning algorithms in neural networks , 1991 .

[38]  Amir F. Atiya,et al.  Application of the recurrent multilayer perceptron in modeling complex process dynamics , 1994, IEEE Trans. Neural Networks.

[39]  R. V. Dooren,et al.  A Chebyshev technique for solving nonlinear optimal control problems , 1988 .