Title :
Location and stability of the high-gain equilibria of nonlinear neural networks
Author :
Vidyasagar, Mathukumalli
Author_Institution :
Centre for Artificial Intelligence & Robotics, Bangladore, India
fDate :
7/1/1993 12:00:00 AM
Abstract :
The author analyzes the number, location, and stability behavior of the equilibria of arbitrary nonlinear neural networks without resorting to energy arguments based on assumptions of symmetric interactions or no self-interactions. The class of networks studied consists of very general continuous-time continuous-state (CTCS) networks that contain the standard Hopfield network as a special case. The emphasis is on the case where the slopes of the sigmoidal nonlinearities become larger and larger
Keywords :
neural nets; stability; Hopfield network; continuous-time continuous-state networks; high-gain equilibria; location; nonlinear neural networks; sigmoidal nonlinearities; stability; Artificial intelligence; Artificial neural networks; Computer networks; Concurrent computing; Hopfield neural networks; Hypercubes; Intelligent robots; Neural networks; Neurons; Stability analysis;
Journal_Title :
Neural Networks, IEEE Transactions on
