Title :
Neuron model with potential applications in pulse-stream neural nets
Author :
Gan, Q. ; Wei, Y.
Author_Institution :
Dept. of Biomed. Eng., Southeast Univ., Nanjing, China
fDate :
4/9/1992 12:00:00 AM
Abstract :
A variant of the FitzHugh-Nagumo model is proposed. Computer simulation results show that the variant neuron model has the property that its threshold, refractory period and response amplitude can be dynamically adjusted. Some problems related to collective property, learning and implementation of the neural network based on the proposed neuron model are discussed. It is noted that the variant model has potential applications in pulse-stream neural networks.
Keywords :
brain models; learning systems; neural nets; FitzHugh-Nagumo model; collective property; learning; pulse-stream neural nets; refractory period; response amplitude; threshold; variant neuron model;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19920477