Title :
Fixed point analysis for discrete-time recurrent neural networks
Author_Institution :
Dept. of Maths., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
The author shows the existence of a fixed point for every recurrent neural network and uses a geometric approach to locate where the fixed points are. The stability is discussed for low-gain and high-gain situations. A generalized Hopfield saturation theorem is presented in a high gain situation for a discrete-time model version
Keywords :
discrete time systems; geometry; recurrent neural nets; stability; discrete-time recurrent neural networks; fixed point analysis; generalized Hopfield saturation theorem; geometric approach; high-gain; low-gain; stability; Difference equations; Differential equations; Hopfield neural networks; Mathematics; Neural networks; Neurons; Nonlinear dynamical systems; Recurrent neural networks; Stability;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227277
