Abstract
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.
Original language | English |
---|---|
Title of host publication | ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing |
Subtitle of host publication | Computational Intelligence for the E-Age |
Editors | Jagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Pages | 243-247 |
Number of pages | 5 |
Volume | 1 |
ISBN (Electronic) | 9810475241, 9789810475246 |
DOIs | |
Publication status | Published - Jan 1 2002 |
Event | 9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore Duration: Nov 18 2002 → Nov 22 2002 |
Other
Other | 9th International Conference on Neural Information Processing, ICONIP 2002 |
---|---|
Country/Territory | Singapore |
City | Singapore |
Period | 11/18/02 → 11/22/02 |
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications
- Information Systems
- Signal Processing