Multi-branch structure of Layered Neural Networks

Takashi Yamashita; Kotaro Hirasawa; Jinglu Hu; Junichi Murata

doi:10.11499/sicep.2002.0.163.0

SICE Annual Conference 2002

DOI https://doi.org/10.11499/sicep.2002.0.163.0

会議情報

主催: The Society of Instrument and Control Engineers

共催: IEEE/Industiral Electronic Society, IEEE/Robotics and Automation Society, IEEE/Control System Society

Multi-branch structure of Layered Neural Networks

Takashi Yamashita, Kotaro Hirasawa, Jinglu Hu, Junichi Murata

著者情報

キーワード: Neural Networks, Universal Learning Networks, Multi-branch

会議録・要旨集フリー

p. 163

詳細

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.

責任著者(Corresponding author)

J-STAGEへの登録はこちら（無料）