抄録
In this paper, a multi-branch structure of neural networks is studied to make their size compact. The multi-branch structure has shown improved performance against conventional neural networks. As a result, it has been proved that the number of nodes of networks and the computational cost for training networks can be reduced. In addition, it could be said that proposed multi-branch networks are special cases of higher order neural networks, however, they obtain higher order effect easier without suffering the parameter explosion problem.
本文言語 | 英語 |
---|---|
ホスト出版物のタイトル | ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing |
ホスト出版物のサブタイトル | Computational Intelligence for the E-Age |
編集者 | Jagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee |
出版社 | Institute of Electrical and Electronics Engineers Inc. |
ページ | 243-247 |
ページ数 | 5 |
巻 | 1 |
ISBN(電子版) | 9810475241, 9789810475246 |
DOI | |
出版ステータス | 出版済み - 1月 1 2002 |
イベント | 9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, シンガポール 継続期間: 11月 18 2002 → 11月 22 2002 |
その他
その他 | 9th International Conference on Neural Information Processing, ICONIP 2002 |
---|---|
国/地域 | シンガポール |
City | Singapore |
Period | 11/18/02 → 11/22/02 |
!!!All Science Journal Classification (ASJC) codes
- コンピュータ ネットワークおよび通信
- 情報システム
- 信号処理