Universal learning networks with branch control

K. Hirasawa, Jinglu Hu, Qingyu Xiong, J. Murata, Y. Shiraishi
2000 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium  
In this paper, Universal Learning Network with Branch Control (ULN with BC) is proposed, which consists of basic networks and branch control networks. The branch control network can be used to determine which branches of the basic network should be used. This determination depends on the inputs or the network flow of the basic network. Therefore, by using the ULN with BC, locally functions distributed networks can be realized depending on the values of the inputs of the network or the
more » ... n of the network flow. The proposed network is applied to some function approximation problems. The simulation results show that the ULN with BC exhibits better performance than the conventional networks with comparable complexity.
doi:10.1109/ijcnn.2000.861287 dblp:conf/ijcnn/HirasawaHXMS00 fatcat:ts35hzlu4jfcfgribknm2ftyuq