| Presentation | 1999/11/26 Incremental Learning for Optimal Generalization in a Family of Projection Learings Eiji NISHI, Masashi SUGIYAMA, Hidemitsu OGAWA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We consider the case where new training examples are added to acquire a higher level of generalization capability after the learning process has been completed. In this case, incremental learning is generally preferred because it is more efficient in computation than batch learning. In this paper, we propose an incremental learning method for a family of projection learnings, which is a collection of an infinite kinds of learnings including projection learning, partial projection learning, and averaged projection learning, The proposed method is optimal in the sense of the generalization capability, i. e., it provides exactly the same generalization capability as that obtained by batch learning. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | supervised learning / generalization capability / a family of projection learnings / batch learning / incremental learning |
| Paper # | NC99-55 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1999/11/26(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) | Incremental Learning for Optimal Generalization in a Family of Projection Learings |
| Sub Title (in English) | |
| Keyword(1) | supervised learning |
| Keyword(2) | generalization capability |
| Keyword(3) | a family of projection learnings |
| Keyword(4) | batch learning |
| Keyword(5) | incremental learning |
| 1st Author's Name | Eiji NISHI |
| 1st Author's Affiliation | Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology.() |
| 2nd Author's Name | Masashi SUGIYAMA |
| 2nd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology. |
| 3rd Author's Name | Hidemitsu OGAWA |
| 3rd Author's Affiliation | Department of Computer Science, Tokyo Institute of Technology. |
| Date | 1999/11/26 |
| Paper # | NC99-55 |
| Volume (vol) | vol.99 |
| Number (no) | 473 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |