抄録
In training a neural network we usually have to create a set of learning samples, which is a number of sample problem and desired output pairs. However sometimes it is difficult to provide an effective learning sample especially when the structure of the pattern space is complex. In this paper we introduce an algorithm that can actively self produce the effective sample pattern while advancing the learning process.
| 本文言語 | English |
|---|---|
| ホスト出版物のタイトル | Proceedings of the International Joint Conference on Neural Networks |
| Place of Publication | Piscataway, NJ, United States |
| 出版社 | Publ by IEEE |
| ページ | 2548-2551 |
| ページ数 | 4 |
| 巻 | 3 |
| ISBN（印刷版） | 0780314212, 9780780314214 |
| 出版ステータス | Published - 1993 |
| イベント | Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn 継続期間: 1993 10月 25 → 1993 10月 29 |
Other
| Other | Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) |
|---|---|
| City | Nagoya, Jpn |
| Period | 93/10/25 → 93/10/29 |
ASJC Scopus subject areas
- 工学（全般）