Local stability conditions for discrete-time cascade locally recurrent neural networks

Local stability conditions for discrete-time cascade locally recurrent neural networks The paper deals with a specific kind of discrete-time recurrent neural network designed with dynamic neuron models. Dynamics are reproduced within each single neuron, hence the network considered is a locally recurrent globally feedforward. A crucial problem with neural networks of the dynamic type is stability as well as stabilization in learning problems. The paper formulates local stability conditions for the analysed class of neural networks using Lyapunov's first method. Moreover, a stabilization problem is defined and solved as a constrained optimization task. In order to tackle this problem, a gradient projection method is adopted. The efficiency and usefulness of the proposed approach are justified by using a number of experiments.

[1]  K. Patan.  Stability Criteria for Three-Layer Locally Recurrent Networks , 2008 .

[2]  M. Gori,et al.  BPS: a learning algorithm for capturing the dynamic nature of speech , 1989, International 1989 Joint Conference on Neural Networks.

[3]  Paul M. Frank,et al.  Development of Dynamic Neural Networks With Application to Observer-Based Fault Detection and Izolation , 1999 .

[4]  Giovanni Soda,et al.  Local Feedback Multilayered Networks , 1992, Neural Computation.

[5]  Jie Zhang,et al.  Long-term prediction models based on mixed order locally recurrent neural networks , 1998 .

[6]  Madan M. Gupta,et al.  Dynamic Neural Units with Applications to the Control of Unknown Nonlinear Systems , 1993, J. Intell. Fuzzy Syst..

[7]  Duccio Papini,et al.  Global exponential stability and global convergence in finite time of delayed neural networks with infinite gain , 2005, IEEE Transactions on Neural Networks.

[8]  Thomas Parisini,et al.  Identification of neural dynamic models for fault detection and isolation: the case of a real sugar evaporation process , 2005 .

[9]  Jinde Cao,et al.  Global Asymptotical Stability of Recurrent Neural Networks With Multiple Discrete Delays and Distributed Delays , 2006, IEEE Transactions on Neural Networks.

[10]  M. Marchesi,et al.  Learning of Chua's circuit attractors by locally recurrent neural networks , 2001 .

[11]  Krzysztof Patan,et al.  Approximation of state-space trajectories by locally recurrent globally feed-forward neural networks , 2008, Neural Networks.

[12]  Ah Chung Tsoi,et al.  Locally recurrent globally feedforward networks: a critical review of architectures , 1994, IEEE Trans. Neural Networks.

[13]  Madan M. Gupta,et al.  Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory , 2003 .

[14]  Ah Chung Tsoi,et al.  FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling , 1991, Neural Computation.

[15]  Krzysztof Patan,et al.  Artificial Neural Networks for the Modelling and Fault Diagnosis of Technical Processes , 2008 .

[16]  K. Patan.  Stability Analysis and the Stabilization of a Class of Discrete-Time Dynamic Neural Networks , 2007, IEEE Transactions on Neural Networks.

[17]  F. Piazza,et al.  Intrinsic stability-control method for recursive filters and neural networks , 2000 .

[18]  Sabri Arik,et al.  Global stability analysis of neural networks with multiple time varying delays , 2005, IEEE Transactions on Automatic Control.

[19]  Jing Yang,et al.  Fault detection and diagnosis of permanent-magnet DC motor based on parameter estimation and neural network , 2000, IEEE Trans. Ind. Electron..