A Study on Layer Connection Strategies in Stacked Convolutional Deep Belief Networks

摘要：

　　This paper presents a study on the layer connections in stacked convolutional networks.To this purpose,three layer connection types namely: diverging connection,neighboring connection and full connection have been compared in convolutional deep belief networks (CDBN).The results showed that our proposed full connection could achieve better performance,a lower time and space cost in nearly all conditions compared with the other two strategies.It can be found that full connection strategy combined the features achieved from lower layers well and made a better typical higher layer features.

关键词： convolutional RBM convolutional deep belief networks full connection diverging connection neighboring connection parameters chosen

作者: Lei Guo Shijie Li Xin Niu Yong Dou

作者单位: National Laboratory for Parallel and Distributed Processing,National University of Defense Technology,410073,Changsha,China

会议类型: 国际会议

会议名称: Chinese Conference on Pattern Recognition, CCPR(2014年全国模式识别学术会议)

会议地点: 长沙

会议语种:英文

页码: 81-90

在线出版日期: 2014-11-01（万方平台首次上网日期，不代表论文的发表时间）