Title :
Global stability of Hopfield neural networks
Author_Institution :
Lab. of Artificial Neural Network, Acad. Sinica, Beijing, China
Abstract :
This paper gives a condition for the global stability of a continuous-time Hopfield neural network when its activation function may not be monotonically increasing. The global stability is proven by constructing a new energy function
Keywords :
Hopfield neural nets; continuous time systems; stability; Hopfield neural networks; activation function; continuous-time HNN; energy function; global stability; Artificial neural networks; Associative memory; Circuits and systems; Hopfield neural networks; Laboratories; Neural networks; Neurons; Stability;
Conference_Titel :
Signal Processing Proceedings, 1998. ICSP '98. 1998 Fourth International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-4325-5
DOI :
10.1109/ICOSP.1998.770857
