Third International Conference on Information Technology and Applications (ICITA'05) Volume 1 Fast Learning Neural Network with Modified Neurons Sydney, Australia July 04-July 07 ISBN: 0-7695-2316-1
In this paper, a neural model with modified neurons is developed. Compare with traditional neural network, such a neural model not only has a fast learning, but also can significantly improve the accuracy while it is used in real applications. To demonstrate the learning efficiency of neural model we developed, a nonlinear system identification problem is studied and simulated. A simulations are performed by using constant learning rates (0.1-0.9). From the simulation results. the neural model we developed obviously has excellent performances as desired.
Index Terms:
neural model, modified neurons, fast learning, accuracy
Citation:
Rey-Chue Hwang, Yu-Ju Chen, Shang-Jen Chuang, Huang-Chu Huang, Wei-Der Chang, "Fast Learning Neural Network with Modified Neurons," icita, vol. 1, pp.313-318, Third International Conference on Information Technology and Applications (ICITA'05) Volume 1, 2005 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb