| Presentation | 2003/10/17 An Efficient Method for Evolving Important Training Data Takaharu KAWATSURE, Qiangfu ZHAO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Currently, we have proposed a method for generating comprehensible decision trees through evolution of training data. The biggest problem of this method is that computational effort is large. One of the reasons for this problem is that the number of generations for evolution is large. If we do not know when to stop evolution, the simplest way is to assume sufficient number of generations. In this paper, we try to solve the problem using validation set. The main idea is to validate the generated rule from an objective point of view and to stop the evolution at a proper point. Using this method, the number of generations can be greatly reduced. The error for training data might be increased, but the generalization ability will keep almost the same. The efficiency of the proposed method is verified through experiments with some public databases. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Genetic algorithm / decision tree / cross validation / comprehensible learning |
| Paper # | PRMU2003-129,NC2003-60 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2003/10/17(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) | An Efficient Method for Evolving Important Training Data |
| Sub Title (in English) | |
| Keyword(1) | Genetic algorithm |
| Keyword(2) | decision tree |
| Keyword(3) | cross validation |
| Keyword(4) | comprehensible learning |
| 1st Author's Name | Takaharu KAWATSURE |
| 1st Author's Affiliation | Multimedia Devices Lab, University of Aizu() |
| 2nd Author's Name | Qiangfu ZHAO |
| 2nd Author's Affiliation | Multimedia Devices Lab, University of Aizu |
| Date | 2003/10/17 |
| Paper # | PRMU2003-129,NC2003-60 |
| Volume (vol) | vol.103 |
| Number (no) | 392 |
| Page | pp.pp.- |
| #Pages | 5 |
| Date of Issue | |