Learning Algorithms of Growing Sparse Neural Networks

摘要：

When using sparse neural networks in practice,it is hard to choose a proper connectivity.Based on new discoveries in brain science,two new learning algorithms are developed which change the network’s connection structure at the time of learning,thus an accurate connectivity is not needed.Sparse neural networks reduce the coupling among inputs so fewer connections are needed to meet the fitting requirement.Simulation results show that the new algorithms are effective.

关键词： Sparse Neural Network Generalization Learning Algorithm Connectivity isomorphism

作者: FENG Chao LI Ning LI Shaoyuan

作者单位: Department of Automation,Shanghai Jiao Tong University,Shanghai 200240

会议类型: 国际会议

会议名称: International Conference on Modelling,Identification and Control(模拟、鉴定、控制国际会议)

会议地点: 上海

会议语种:英文

在线出版日期: 2008-06-29（万方平台首次上网日期，不代表论文的发表时间）