Title :
Global asymptotic stability for RNNs with a bipolar activation function
Author :
Krcmar, Igor R. ; Bozic, Milorad M. ; Mandic, Danilo P.
Author_Institution :
Fac. of Electr. Eng., Banjaluka Univ., Bosnia-Herzegovina
Abstract :
Conditions for global asymptotic stability of a nonlinear relaxation process realized by a recurrent neural network with a hyperbolic tangent activation function are provided. This analysis is based upon the contraction mapping theorem and corresponding fixed point iteration. The derived results find their application in the wide area of neural networks for optimization and signal processing
Keywords :
asymptotic stability; recurrent neural nets; transfer functions; bipolar activation function; contraction mapping theorem; fixed point iteration; global asymptotic stability; hyperbolic tangent activation function; nonlinear relaxation process; optimization; signal processing; Contracts; Convergence; Neural networks; Neurofeedback; Neurons; Recurrent neural networks; Signal design; Signal processing; Stability; State-space methods;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on
Conference_Location :
Belgrade
Print_ISBN :
0-7803-5512-1
DOI :
10.1109/NEUREL.2000.902379
