Presentation | 2001/3/16 H_∞-Learning : Global Optimization Approach Kiyoshi NISIYAMA, Kiyohiko SUZUKI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Back propagation(BP)method is widely known as a learning algorithm of layered neural networks. However, the learning rate is too late, and it is strongly affected by the initial values of weight coefficients and thresholds. In this paper, H_∞-learning of layered neural networks is proposed, and a new learning algorithm, called the g-EHF algorithm, is derived from the H_∞-learning, comparing with back propagation(BP)and extended Kalman filter(EKF)learning algorithms. The robustness of H_∞-learning to variances bo the initial weights and incorrect teach data is verified bycomputer simulations. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | learning algorithm / H_∞ theory / neural network / robust / back propagation / Kalman filter |
Paper # | NC2000-158 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2001/3/16(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | H_∞-Learning : Global Optimization Approach |
Sub Title (in English) | |
Keyword(1) | learning algorithm |
Keyword(2) | H_∞ theory |
Keyword(3) | neural network |
Keyword(4) | robust |
Keyword(5) | back propagation |
Keyword(6) | Kalman filter |
1st Author's Name | Kiyoshi NISIYAMA |
1st Author's Affiliation | Department of Computer and Information Science, Iwate University() |
2nd Author's Name | Kiyohiko SUZUKI |
2nd Author's Affiliation | Department of Computer and Information Science, Iwate University |
Date | 2001/3/16 |
Paper # | NC2000-158 |
Volume (vol) | vol.100 |
Number (no) | 688 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |