wanghongjun
Research Associate
Supervisor of Master's Candidates
- Master Tutor
- Education Level:PhD graduate
- Degree:Doctor of engineering
- Business Address:犀浦3号教学楼31529
- Professional Title:Research Associate
- Alma Mater:四川大学
- Supervisor of Master's Candidates
- School/Department:计算机与人工智能学院
- Discipline:Electronic Information
Software Engineering
Computer Application Technology
Contact Information
- PostalAddress:
- Email:
- Paper Publications
Restricted Boltzmann machines with Gaussian visible units guided by pairwise constraints
- Impact Factor:19.118
- DOI number:10.1109/TCYB.2018.2863601
- Affiliation of Author(s):西南交通大学
- Journal:IEEE Transactions on Cybernetics
- Place of Publication:UNITED STATES
- Key Words:Contrastive divergence (CD), pairwise constraints (PCs), restricted Boltzmann machine (RBM), semi-supervised clustering, unsupervised clustering
- Abstract:Restricted Boltzmann machines (RBMs) and their variants are usually trained by contrastive divergence (CD) learning, but the training procedure is an unsupervised learning approach, without any guidances of the background knowledge. To enhance the expression ability of traditional RBMs, in this paper, we propose pairwise constraints (PCs) RBM with Gaussian visible units (pcGRBM) model, in which the learning procedure is guided by PCs and the process of encoding is conducted under these guidances. The PCs are encoded in hidden layer features of pcGRBM. Then, some pairwise hidden features of pcGRBM flock together and another part of them are separated by the guidances. In order to deal with real-valued data, the binary visible units are replaced by linear units with Gaussian noise in the pcGRBM model. In the learning process of pcGRBM, the PCs are iterated transitions between visible and hidden units during CD learning procedure. Then, the proposed model is inferred by approximative gradient descent method and the corresponding learning algorithm is designed. In order to compare the availability of pcGRBM and traditional RBMs with Gaussian visible units, the features of the pcGRBM and RBMs hidden layer are used as input “data” for K-means, spectral clustering (SP) and affinity propagation (AP) algorithms, respectively. We also use tenfold cross-validation strategy to train and test pcGRBM model to obtain more meaningful results with PCs which are derived from incremental sampling procedures. A thorough experimental evaluation is performed with 12 image datasets of Microsoft Research Asia Multimedia. The experimental results show that the clustering performance of K-means, SP, and AP algorithms based on pcGRBM model are significantly better than traditional RBMs. In addition, the pcGRBM model for clustering tasks shows better performance than some semi-supervised clustering algorithms.
- Co-author:Hua Meng, Peng Jin,Tianrui Li
- First Author:Jielei Chu
- Indexed by:Academic papers
- Correspondence Author:Hongjun Wang
- Document Code:20183605782787
- Discipline:Engineering
- First-Level Discipline:Computer Science and Technology
- Page Number:4321 - 4334
- ISSN No.:2168-2275
- Translation or Not:no
- Date of Publication:2018-08-23