Contrastive Divergence Learning of Restricted Boltzmann Machine

摘要：

Deep Belief Network (DBN) recently introduced by Hinton is a kind of deep architectures which have been applied with success in many machine learning tasks. DBN is based on Restricted Boltzmann Machine (RBM), which is a particular energy-based model. In this paper, we lay more emphasis on the modeling process and learning algorithm of the RBM. Furthermore, we design two kinds of experiments to prove the efficiency of the algorithm based on synthetic dataset and real dataset. The reconstruction data experiments are aimed at proving the convergence of the learning algorithm.The classification experiments are designed to testify the efficiency of the trained models.The result shows that contrastive divergence learning is an effective training algorithm for the RBM model.

关键词： Restricted BoltzmannMachine Contrastive Divergence Learning Markov chain

作者: LIU Jian-wei CHI Guang-hui LUO Xiong-lin

作者单位: Department of Automation China University of Petroleum Beijing, China

会议类型: 国际会议

会议名称: 2012 International Conference on Electric Technology and Civil Engineering(2012 电子技术与土木工程国际会议 ICETCE 2012)

会议地点: 三峡

会议语种:英文

页码: 3049-3052

在线出版日期: 2012-05-18（万方平台首次上网日期，不代表论文的发表时间）