Multi-branch structure of layered neural networks
Takashi Yamashita, Kotaro Hirasawa, Jinglu Hu, J. Murata · 2004
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.