Multi-branch structure of layered neural networks

T. Yamashita, K. Hirasawa, Jinglu Hu, Junichi Murata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)


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 languageEnglish
Title of host publicationICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publicationComputational Intelligence for the E-Age
EditorsJagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages5
ISBN (Electronic)9810475241, 9789810475246
Publication statusPublished - Jan 1 2002
Event9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
Duration: Nov 18 2002Nov 22 2002


Other9th International Conference on Neural Information Processing, ICONIP 2002

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing


Dive into the research topics of 'Multi-branch structure of layered neural networks'. Together they form a unique fingerprint.

Cite this