On-line neural training algorithm with sliding mode control and adaptive learning rate

This paper presents a new algorithm for on-line artificial neural networks (ANN) training. The network topology is a standard multilayer perceptron (MLP) and the training algorithm is based on the theory of variable structure systems (VSS) and sliding mode control (SMC). The main feature of this novel procedure is the adaptability of the gain (learning rate), which is obtained from sliding mode surface so that system stability is guaranteed.

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

[2]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

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

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

[5]  Y. Zhao.  On-line neural network learning algorithm with exponential convergence rate , 1996 .

[6]  Jennie Si,et al.  Advanced neural-network training algorithm with reduced complexity based on Jacobian deficiency , 1998, IEEE Trans. Neural Networks.

[7]  Okyay Kaynak,et al.  Stabilizing and robustifying the learning mechanisms of artificial neural networks in control engineering applications , 2000 .

[8]  Bhaskar D. Rao,et al.  A generalized learning paradigm exploiting the structure of feedforward neural networks , 1996, IEEE Trans. Neural Networks.

[9]  Xinghuo Yu,et al.  A general backpropagation algorithm for feedforward neural networks learning , 2002, IEEE Trans. Neural Networks.

[10]  Zhihong Man,et al.  Adaptive sliding mode approach for learning in a feedforward neural network , 2005, Neural Computing & Applications.

[11]  Vadim I. Utkin,et al.  Sliding Modes and their Application in Variable Structure Systems , 1978 .

[12]  Okyay Kaynak,et al.  Variable structure systems approach for on-line learning in multilayer artificial neural networks , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

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

[14]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[15]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[16]  John Y. Hung,et al.  Variable structure control: a survey , 1993, IEEE Trans. Ind. Electron..