A New Approach for Estimating the Attraction Domain for Hopfield-Type Neural Networks

In this letter, using methods proposed by E. Kaslik, St. Balint, and their colleagues, we develop a new method, expansion approach, for estimating the attraction domain of asymptotically stable equilibrium points of Hopfield-type neural networks. We prove theoretically and demonstrate numerically that the proposed approach is feasible and efficient. The numerical results that obtained in the application examples, including the network system considered by E. Kaslik, L. Brescu, and St. Balint, indicate that the proposed approach is able to achieve better attraction domain estimation.

[1]  Cornelius T. Leondes,et al.  Neural network systems techniques and applications , 1998 .

[2]  Graziano Chesi,et al.  Computing output feedback controllers to enlarge the domain of attraction in polynomial systems , 2004, IEEE Transactions on Automatic Control.

[3]  Tsu-Tian Lee,et al.  $H^\infty$ Controller Parameterization for General Discrete-Time Nonlinear Systems , 2003 .

[4]  St. Balint,et al.  Gradual approximation of the domain of attraction by gradual extension of the , 2002 .

[5]  Heinz Schättler,et al.  Stability Regions for Differential-Algebraic Systems , 1992 .

[6]  Masahiko Morita,et al.  Associative memory with nonmonotone dynamics , 1993, Neural Networks.

[7]  Stefan Balint,et al.  On the controllability of the continuous-time Hopfield-type neural networks , 2005, Seventh International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC'05).

[8]  E. Kaslik,et al.  Methods for determination and approximation of the domain of attraction , 2004 .

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

[10]  David Burshtein.  Long-term attraction in higher order neural networks , 1998, IEEE Trans. Neural Networks.

[11]  E. Kaslik,et al.  Control procedures using domains of attraction , 2005 .

[12]  Stefan Balint,et al.  Configurations of steady states for Hopfield-type neural networks , 2006, Appl. Math. Comput..

[13]  Pauline van den Driessche,et al.  Global Attractivity in Delayed Hopfield Neural Network Models , 1998, SIAM J. Appl. Math..

[14]  St. Balint,et al.  Methods for determination and approximation of the domain of attraction in the case of autonomous discrete dynamical systems , 2004 .