A New Adaptive Backpropagation Algorithm Based on Lyapunov Stability Theory for Neural Networks

A new adaptive backpropagation (BP) algorithm based on Lyapunov stability theory for neural networks is developed in this paper. It is shown that the candidate of a Lyapunov function V(k) of the tracking error between the output of a neural network and the desired reference signal is chosen first, and the weights of the neural network are then updated, from the output layer to the input layer, in the sense that DeltaV(k)=V(k)-V(k-1)<0. The output tracking error can then asymptotically converge to zero according to Lyapunov stability theory. Unlike gradient-based BP training algorithms, the new Lyapunov adaptive BP algorithm in this paper is not used for searching the global minimum point along the cost-function surface in the weight space, but it is aimed at constructing an energy surface with a single global minimum point through the adaptive adjustment of the weights as the time goes to infinity. Although a neural network may have bounded input disturbances, the effects of the disturbances can be eliminated, and asymptotic error convergence can be obtained. The new Lyapunov adaptive BP algorithm is then applied to the design of an adaptive filter in the simulation example to show the fast error convergence and strong robustness with respect to large bounded input disturbances

[1]  Johan A. K. Suykens,et al.  NLq theory: checking and imposing stability of recurrent neural networks for nonlinear modeling , 1997, IEEE Trans. Signal Process..

[2]  Alexander S. Poznyak,et al.  Differential Neural Networks for Robust Nonlinear Control: Identification, State Estimation and Trajectory Tracking , 2001 .

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

[4]  Jin Zhang,et al.  Output feedback control of a class of discrete MIMO nonlinear systems with triangular form inputs , 2005, IEEE Transactions on Neural Networks.

[5]  Cong Wang,et al.  Learning from neural control , 2006, IEEE Transactions on Neural Networks.

[6]  Jose C. Principe,et al.  Neural and adaptive systems , 2000 .

[7]  Shuzhi Sam Ge,et al.  Stable adaptive control and estimation for nonlinear systems - neural and fuzzy approximator techniques: J. T. Spooner, M. Maggiore, R. Ordóñez, K. M. Passino, John Wiley & Sons, Inc., New York, 2002, ISBN: 0-471-41546-4 , 2003, Autom..

[8]  Eliezer Colina-Morles,et al.  A sliding mode strategy for adaptive learning in Adalines , 1995 .

[9]  Antônio de Pádua Braga,et al.  Sliding mode algorithm for training multilayer artificial neural networks , 1998 .

[10]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[11]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[12]  Eric A. Wan,et al.  Relating Real-Time Backpropagation and Backpropagation-Through-Time: An Application of Flow Graph Interreciprocity , 1994, Neural Computation.

[13]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[14]  Eric A. Wan,et al.  Temporal backpropagation for FIR neural networks , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[15]  Zhihong Man,et al.  Design of Adaptive Filters Using Lyapunov Stability Theory , 1998 .

[16]  Kevin M. Passino,et al.  Stable Adaptive Control and Estimation for Nonlinear Systems , 2001 .

[17]  Naira Hovakimyan,et al.  Neural network adaptive control for nonlinear nonnegative dynamical systems , 2005, IEEE Transactions on Neural Networks.

[18]  Zhihong Man,et al.  Lyapunov-theory-based radial basis function networks for adaptive filtering , 2002 .

[19]  G. W. Ng application of Neural Networks to Adaptive Control of Nonlinear Systems , 1997 .

[20]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[21]  Kok Kiong Tan,et al.  Nonlinear adaptive control of interconnected systems using neural networks , 2006, IEEE Transactions on Neural Networks.

[22]  Heidar Ali Talebi,et al.  A stable neural network-based observer with application to flexible-joint manipulators , 2006, IEEE Transactions on Neural Networks.

[23]  Okyay Kaynak,et al.  The fusion of computationally intelligent methodologies and sliding-mode control-a survey , 2001, IEEE Trans. Ind. Electron..