Title :
A pulsed neural network capable of universal approximation
Author :
Cotter, Neil E. ; Mian, Omar N.
Author_Institution :
Dept. of Electr. Eng., Utah Univ., Salt Lake City, UT, USA
fDate :
3/1/1992 12:00:00 AM
Abstract :
The authors describe a pulsed network version of the cerebellar model articulation controller (CMAC), popularized by Albus (1981). The network produces output pulses whose times of occurrence are a function of input pulse intervals. Within limits imposed by causality conditions, this function can approximate any bounded measurable function on a compact domain. Simulation results demonstrate the viability of training the network with a least mean square algorithm
Keywords :
function approximation; least squares approximations; neural nets; physiological models; bounded measurable function; causality conditions; cerebellar model articulation controller; function approximation; least mean square algorithm; physiological models; pulsed neural network; universal approximation; Biological information theory; Biological neural networks; Biological system modeling; Least mean square algorithms; Least squares approximation; Mathematical model; Nervous system; Neural networks; Neurons; Timing;
Journal_Title :
Neural Networks, IEEE Transactions on
