Title :
Numerical modeling of continuous-time fully coupled neural networks
Author :
Zurada, Jacek M. ; Kang, M.J.
Author_Institution :
Dept. of Electr. Eng., Louisville Univ., KY, USA
Abstract :
Numerical performance modeling of fully coupled continuous-time networks utilizing continuous activation functions, finite input resistance of neurons, and other parasitic components within the neural systems is discussed. Both time-domain performance modeling and static numerical modeling of the networks are characterized and compared. The main focus is the dynamic and static numerical modeling of actual Hopfield-type networks
Keywords :
approximation theory; neural nets; relaxation theory; time-domain analysis; Hopfield-type networks; continuous activation functions; continuous-time fully coupled neural networks; dynamic numerical modelling; finite input resistance; numerical performance modelling; parasitic components; static numerical modeling; time-domain performance modeling; Capacitance; Convergence; Electric resistance; Equations; Neural networks; Neurofeedback; Neurons; Numerical models; Time domain analysis; Voltage;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170655
