Access the full text.
Sign up today, get DeepDyve free for 14 days.
Marc'Aurelio Ranzato, A. Krizhevsky, Geoffrey Hinton (2010)
Factored 3-Way Restricted Boltzmann Machines For Modeling Natural Images
T. Tieleman (2008)
Training restricted Boltzmann machines using approximations to the likelihood gradient
Jinhui Tang, Xiangbo Shu, Zechao Li, Yu-Gang Jiang, Qi Tian (2018)
Social Anchor-Unit Graph Regularized Tensor Completion for Large-Scale Image RetaggingIEEE Transactions on Pattern Analysis and Machine Intelligence, 41
R. Salakhutdinov, Geoffrey Hinton (2009)
Replicated Softmax: an Undirected Topic Model
Z. Zhu, S. Jia, S. He, Y. Sun, Z. Ji, L. Shen (2015)
Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic frameworkInformation Sciences, 298
Chen Chen, Hanghang Tong, Lei Xie, Lei Ying, Qing He (2017)
Cross-Dependency Inference in Multi-Layered NetworksACM Transactions on Knowledge Discovery from Data (TKDD), 11
Lok-Won Kim (2018)
DeepX: Deep Learning Accelerator for Restricted Boltzmann Machine Artificial Neural NetworksIEEE Transactions on Neural Networks and Learning Systems, 29
Evangelos Papalexakis, Christos Faloutsos, N. Sidiropoulos (2015)
ParCube: Sparse Parallelizable CANDECOMP-PARAFAC Tensor DecompositionACM Trans. Knowl. Discov. Data, 10
Jianchao Yang, John Wright, Thomas Huang, Yi Ma (2010)
Image Super-Resolution Via Sparse RepresentationIEEE Transactions on Image Processing, 19
I. Oseledets (2011)
Tensor-Train DecompositionSIAM J. Sci. Comput., 33
Guanglei Qi, Yanfeng Sun, Junbin Gao, Yongli Hu, Jinghua Li (2016)
Matrix Variate Restricted Boltzmann Machine2016 International Joint Conference on Neural Networks (IJCNN)
Geoffrey Hinton, Simon Osindero, Y. Teh (2006)
A Fast Learning Algorithm for Deep Belief NetsNeural Computation, 18
(2011)
Sparse autoencoder
W. Wong, Zhihui Lai, Yong Xu, J. Wen, Chu Ho (2015)
Joint Tensor Feature Analysis For Visual Object RecognitionIEEE Transactions on Cybernetics, 45
Jinhui Tang, Xiangbo Shu, Guo-Jun Qi, Zechao Li, Meng Wang, Shuicheng Yan, R. Jain (2017)
Tri-Clustered Tensor Completion for Social-Aware Image Tag RefinementIEEE Transactions on Pattern Analysis and Machine Intelligence, 39
Zexuan Zhu, Sen Jia, Shan He, Yiwen Sun, Z. Ji, Linlin Shen (2014)
University of Birmingham Three-dimensional Gabor feature extraction for hyperspectral imagery classification using a memetic framework
Nian Cai, Zhenghang Su, Zhineng Lin, Han Wang, Zhijing Yang, B. Ling (2017)
Blind inpainting using the fully convolutional neural networkThe Visual Computer, 33
Jianguang Zhang, Yahong Han, Jianmin Jiang (2015)
Tensor rank selection for multimedia analysisJ. Vis. Commun. Image Represent., 30
R. Socher, Danqi Chen, Christopher Manning, A. Ng (2013)
Reasoning With Neural Tensor Networks for Knowledge Base Completion
Radford Neal (2006)
Pattern Recognition and Machine LearningPattern Recognition and Machine Learning
Geoffrey Hinton (2002)
Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 14
Hanwang Zhang, Yang Yang, Huanbo Luan, Shuicheng Yan, Tat-Seng Chua (2014)
Start from Scratch: Towards Automatically Identifying, Modeling, and Naming Visual AttributesProceedings of the 22nd ACM international conference on Multimedia
Alexander Novikov, D. Podoprikhin, A. Osokin, D. Vetrov (2015)
Tensorizing Neural Networks
S. Soundarajan, J. Hopcroft (2015)
Use of Local Group Information to Identify Communities in NetworksACM Transactions on Knowledge Discovery from Data (TKDD), 9
Yoshua Bengio (2007)
Learning Deep Architectures for AIFound. Trends Mach. Learn., 2
Li-Yu Liu, Cai-ming Zhang, Q. Guo, Hui Xu, Yuanfeng Zhou (2016)
Adaptive sparse coding on PCA dictionary for image denoisingThe Visual Computer, 32
Shan He, Huanhuan Chen, Zexuan Zhu, Douglas Ward, Helen Cooper, M. Viant, John Heath, Xin Yao (2015)
Robust twin boosting for feature selection from high-dimensional omics data with label noiseInf. Sci., 291
Sangwoo Lee, Younghui Kim, Jungjin Lee, Kyehyun Kim, Kyunghan Lee, Jun-yong Noh (2014)
Depth manipulation using disparity histogram analysis for stereoscopic 3DThe Visual Computer, 30
T. Kolda, Brett Bader (2009)
Tensor Decompositions and ApplicationsSIAM Rev., 51
C. Chen, H. Tong, L. Xie, L. Ying, Q. He (2017)
Cross-dependency inference in multi-layered networks: A collaborative filtering perspectiveACM Transactions on Knowledge Discovery from Data 2016 Special Issue, 2016
Meng Yang, Peng Zhu, Feng Liu, L. Shen (2015)
Joint representation and pattern learning for robust face recognitionNeurocomputing, 168
T. Nguyen, T. Tran, Dinh Phung, S. Venkatesh (2015)
Tensor-Variate Restricted Boltzmann Machines
Yue Wu, S. Hoi, Tao Mei, Nenghai Yu (2014)
Large-Scale Online Feature Selection for Ultra-High Dimensional Sparse DataACM Transactions on Knowledge Discovery from Data (TKDD), 11
Restricted Boltzmann machine (RBM) is a famous model for feature extraction and can be used as an initializer for neural networks. When applying the classic RBM to multidimensional data such as 2D/3D tensors, one needs to vectorize such as high-order data. Vectorizing will result in dimensional disaster and valuable spatial information loss. As RBM is a model with fully connected layers, it requires a large amount of memory. Therefore, it is difficult to use RBM with high-order data on low-end devices. In this article, to utilize classic RBM on tensorial data directly, we propose a new tensorial RBM model parameterized by the tensor train format (TTRBM). In this model, both visible and hidden variables are in tensorial form, which are connected by a parameter matrix in tensor train format. The biggest advantage of the proposed model is that TTRBM can obtain comparable performance compared with the classic RBM with much fewer model parameters and faster training process. To demonstrate the advantages of TTRBM, we conduct three real-world applications, face reconstruction, handwritten digit recognition, and image super-resolution in the experiments.
ACM Transactions on Knowledge Discovery from Data (TKDD) – Association for Computing Machinery
Published: Jun 7, 2019
Keywords: Tensor
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.