Title :
Two adaptation methods of artificial neural networks
Author :
Sun, Baocheng ; Zhang, Zhifang
Author_Institution :
China Acad. of Electron. & Inf. Technol., Beijing, China
fDate :
27 Jun-2 Jul 1994
Abstract :
In order to cope with the existing errors in modeling of multilayered feedforward neural networks (MLF), this paper presents two adaptation methods of artificial neural networks: feedback adaptation and Taylor series expansion based adaptation, based on the trained MLF with some modeling errors. Simulation results show that the proposed two adaptation methods give good error-reduction in modeling and forecasting of MLF
Keywords :
error analysis; feedback; feedforward neural nets; modelling; series (mathematics); Taylor series expansion based adaptation; error-reduction; feedback adaptation; forecasting; modeling errors; multilayered feedforward neural networks; Application software; Artificial neural networks; Computer errors; Feedforward neural networks; Multi-layer neural network; Neural networks; Neurofeedback; Neurons; Predictive models; Taylor series;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374749
