抄録
Layered neural networks have such several weak points in the learning algorithm of error back-propagation as terminating at a local optimal solution and requiring its learning for many hours. In this paper an enhanced method for learning algorithm is proposed in order to shorten the learning time less than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as an application of the enhanced learning algorithm of the neural network to the real problem, the neural model of business evaluation based on financial indices is built and its efficiency of the learning was evaluated to shorten the learning time sufficiently up to 64% less than a conventional one.
| 本文言語 | English |
|---|---|
| ホスト出版物のタイトル | IEEE International Conference on Neural Networks - Conference Proceedings |
| Place of Publication | Piscataway, NJ, United States |
| 出版社 | IEEE |
| ページ | 155-160 |
| ページ数 | 6 |
| 巻 | 1 |
| 出版ステータス | Published - 1994 |
| 外部発表 | はい |
| イベント | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA 継続期間: 1994 6月 27 → 1994 6月 29 |
Other
| Other | Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) |
|---|---|
| City | Orlando, FL, USA |
| Period | 94/6/27 → 94/6/29 |
ASJC Scopus subject areas
- ソフトウェア