• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 论文 • 上一篇    下一篇

稀疏受限玻尔兹曼机研究综述

麦超,邹维宝   

  1. (长安大学地质工程与测绘学院,陕西 西安 710054)
  • 收稿日期:2015-12-07 修回日期:2016-03-17 出版日期:2017-07-25 发布日期:2017-07-25

Review of sparse restricted Boltzmann machine

MAI Chao,ZOU Wei-bao   

  1. (College of Geology Engineering and Geomatics,Chang’an University,Xi’an 710054,China)
  • Received:2015-12-07 Revised:2016-03-17 Online:2017-07-25 Published:2017-07-25

摘要:

人类的视觉系统采用稀疏编码方式来描述被感知的图像特征,而稀疏表示被认为是图像特征最合理而且有效的表示形式。由于受限玻尔兹曼机具有强大的无监督学习能力,所以它被用于深度学习中。将多个稀疏受限玻尔兹曼机堆叠起来,不仅可以模拟大脑的分层结构,还可以学习到图像更加抽象的特征信息。因此,采用受限玻尔兹曼机获得图像特征的稀疏表示在人工智能领域得到了广泛的关注。首先介绍了受限玻尔兹曼机的基础知识,紧接着阐述了稀疏化的原因,并描述了稀疏受限玻尔兹曼机的优点。然后,文章详细介绍了稀疏受限波尔兹曼机的国内外研究现状。最后总结了目前研究中存在的问题及将来的发展方向。

 

关键词: 稀疏表示, 受限玻尔兹曼机, 深度学习, 图像处理

Abstract:

Sparse coding is used to describe the image features perceived in the human visual system. Sparse representation is a reasonable and effective representation of image features. We therefore introduce the restricted Boltzmann machine (RBM) to deep learning because of its reliable unsupervised ability to learn image features. Stacked sparse restricted Boltzmann machines (SRBMs) cannot only mimic the hierarchical organization of the cortex but also achieve more abstractive image features. So using the SRBM to obtain the sparse representation of image features attracts more attention in the field of AI. We introduce the basics of the RBM, describe its advantages and review thoroughly the existing work. Finally, we summarize open questions suggested in the last section and the future development.
 

Key words: sparse representation, RBM, deep learning, image processing