Title :
A neural network model with compensating inputs
Author :
Sun, Baocheng ; Zhang, Zhifang
Author_Institution :
Inst. of Autom., Acad. Sinica, Beijing, China
fDate :
27 Jun-2 Jul 1994
Abstract :
In order to overcome the existing error in neural networks modeling, a neural network model with compensating inputs is proposed in this paper. Owing to compensation inputs introduced in the neural network, the proposed neural network model can practically realize neural network modeling with any accuracy and has very good adaptation to the new network inputs. It also has wide range of extensions to other neural network applications. Encouraging results have been obtained in the authors´ simulations
Keywords :
compensation; feedforward neural nets; multilayer perceptrons; adaptation; compensating inputs; neural network model; Application software; Artificial neural networks; Automation; Computer errors; Feedforward neural networks; Information technology; Multi-layer neural network; Neural networks; Neurons; Sun;
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.1994.374206
