| Presentation | 2000/12/1 New structural modification learning algorithm for rule extraction from Neural Networks Nam Thang Hoang, Taichi Hayasaka, Shiro Usui, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The neural network approach has proven useful for a development of artificial intelligence system with capability of dealing with numerical values. However, a disadvantage with this approach is that the knowledge embedded in the neural network is opaque. Several methods have been proposed in order to interpret the knowledge into the form which is easy to understand(e.g. symbolic and simple inequality form), but these approaches can only be applied for simple networks. Therefore, several structural learning method for selecting the most suitable network have been proposed. In this paper, we showed that traditional rule extraction methods are not applicable if the network structure is not optimal. Also, we criticize the heuristic characteristics of these methods. At the end, we propose a new structural learning method for rule extraction problem and demonstrate that it works effectively for noisy data by numerical simulations. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | neural network / rule extraction / structural learning / subset algorithm |
| Paper # | NC2000-77 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2000/12/1(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) | New structural modification learning algorithm for rule extraction from Neural Networks |
| Sub Title (in English) | |
| Keyword(1) | neural network |
| Keyword(2) | rule extraction |
| Keyword(3) | structural learning |
| Keyword(4) | subset algorithm |
| 1st Author's Name | Nam Thang Hoang |
| 1st Author's Affiliation | Dept. of Information and Computer Science, Toyohashi University of Technology() |
| 2nd Author's Name | Taichi Hayasaka |
| 2nd Author's Affiliation | Dept. of Information and Computer Science, Toyohashi University of Technology |
| 3rd Author's Name | Shiro Usui |
| 3rd Author's Affiliation | Dept. of Information and Computer Science, Toyohashi University of Technology |
| Date | 2000/12/1 |
| Paper # | NC2000-77 |
| Volume (vol) | vol.100 |
| Number (no) | 490 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |