Qualitative analysis for recurrent neural networks with linear threshold transfer functions

Multistable networks have attracted much interest in recent years, since multistability is of primary importance for some applications of recurrent neural networks where monostability exhibits some restrictions. This paper focuses on the analysis of dynamical property for a class of additive recurrent neural networks with nonsaturating linear threshold transfer functions. A milder condition is derived to guarantee the boundedness and global attractivity of the networks. Dynamical properties of the equilibria of two-dimensional networks are analyzed theoretically, and the relationships between the equilibria features and network parameters (synaptic weights and external inputs) are revealed. In addition, the sufficient and necessary conditions for coexistence of multiple equilibria are obtained, which confirmed the observations in with a cortex-inspired silicon circuit. The results obtained in this paper are applicable to both symmetric and nonsymmetric networks. Simulation examples are used to illustrate the theory developed in this paper.

[1]  Stephen Grossberg,et al.  Absolute stability of global pattern formation and parallel memory storage by competitive neural networks , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  P. Holmes,et al.  Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields , 1983, Applied Mathematical Sciences.

[3]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[4]  L. Perko.  Differential Equations and Dynamical Systems , 1991 .

[5]  M. Forti.  On Global Asymptotic Stability of a Class of Nonlinear Systems Arising in Neural Network Theory , 1994 .

[6]  H. Sompolinsky,et al.  Theory of orientation tuning in visual cortex. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Jianfeng Feng,et al.  On Neurodynamics with Limiter Function and Linsker's Developmental Model , 1996, Neural Computation.

[8]  Nikola Kasabov,et al.  Brain-like Computing and Intelligent Information Systems , 1998 .

[9]  Jianfeng Feng,et al.  Fixed-Point Attractor Analysis for a Class of Neurodynamics , 1998, Neural Computation.

[10]  Richard H. R. Hahnloser,et al.  On the piecewise analysis of networks of linear threshold neurons , 1998, Neural Networks.

[11]  Zhang Yi,et al.  Estimate of exponential convergence rate and exponential stability for neural networks , 1999, IEEE Trans. Neural Networks.

[12]  Richard Hans Robert Hahnloser,et al.  Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit , 2000, Nature.

[13]  Heiko Wersing,et al.  A Competitive-Layer Model for Feature Binding and Sensory Segmentation , 2001, Neural Computation.

[14]  Heiko Wersing,et al.  Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions , 2001, Neural Computation.

[15]  P. Vadakkepat,et al.  Absolute periodicity and absolute stability of delayed neural networks , 2002 .

[16]  Huajin Tang,et al.  Convergence analysis of discrete time recurrent neural networks for linear variational inequality problem , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[17]  Zhang Yi,et al.  Multistability Analysis for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions , 2003, Neural Computation.

[18]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

[19]  K. Hadeler,et al.  Stationary states of the Hartline-Ratliff model , 1987, Biological Cybernetics.

[20]  Hermann Haken,et al.  Brain dynamics : synchronization and activity patterns in pulse-coupled neural nets with delays and noise , 2006 .