Title :
Adaptive input field neural network
Author_Institution :
NEC Corp., Kanagawa, Japan
Abstract :
Previously, the author presented an adaptive input field neural network (AIFNN) which can appropriately handle positional and temporal variance and distortion. In the present work, the AIFNN convergence is shown by utilizing a Lyapunov function. Two methods for avoiding AIFNN adaptation to an incorrect category are proposed. An AIFNN application-offset and gain adjustment-is proposed
Keywords :
convergence; neural nets; Lyapunov function; adaptive input field neural network; convergence; distortion; gain adjustment; offset; positional variance; temporal variance; Adaptation model; Character recognition; Convergence; Laboratories; Lyapunov method; National electric code; Neural networks; Neurons; Speech recognition;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170385
