Title :
Multi-branch structure of layered neural networks
Author :
Yamashita, T. ; Hirasawa, K. ; Hu, J. ; Murata, J.
Author_Institution :
Graduate Sch. of Inf. Sci & Electr. Eng.., Kyushu Univ., Japan
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.
Keywords :
learning (artificial intelligence); multilayer perceptrons; neural nets; Universal Learning Networks; layered neural networks; multi-branch structure; neural networks; universal learning; Computational efficiency; Delay effects; Differential equations; Gradient methods; Information science; Input variables; Neural networks; Nonlinear equations; Sampling methods;
Conference_Titel :
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN :
0-7803-7631-5
DOI :
10.1109/SICE.2002.1195252
