Learning Algorithms for the Classification Restricted Boltzmann Machine

By Hugo Larochelle, Michael I. Mandel, Razvan Pascanu, Yoshua Bengio. 2012

326 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xiaogang Wang
2. Dacheng Tao
3. Xiaoou Tang
4. Yoshua Bengio
5. Gong Cheng
6. Ping Luo
7. Wanli Ouyang
8. Yi Yang

Citations in the corpus

• Semi-supervised Sequence Learning (2015, neutral): “Hybrid Class RBM [18] 23.”
• Training Restricted Boltzmann Machines (2015, background): “, 2009) or character recognition and text classification problems (Larochelle et al., 2012).”
• Sequence Classification Restricted Boltzmann Machines With Gated Units (2020, background): “It has been shown that learning a local RBM with labels is tractable [18], [19], but learning the entire sequence is not.”
• Training restricted Boltzmann machines: An introduction (2014, methodology): “, 2009) or character recognition and text classification problems (Larochelle et al., 2012).”
• Rotation-Insensitive and Context-Augmented Object Detection in Remote Sensing Images (2018, background): “An important advantage of the discriminative training objective is that it is possible to compute its gradient with respect to the ClassRBM’s [55] parameters exactly.”
• Stochastic Ratio Matching of RBMs for Sparse High-Dimensional Inputs (2013, methodology): “Following Larochelle et al. (2012), we report the classification error and for a fair comparison we use the same preprocessing 1 .”
• General Stochastic Networks for Classification (2014, methodology): “Our approach is related to the generative-discriminative training approach of RBMs [15].”
• Learning Neural Random Fields with Inclusive Auxiliary Generators (2018, methodology): “To the best of our knowledge, the conflict does not seem to be reported in previous generative SSL methods [23], [24] which use the K-class classifier like in semi-supervised inclusive-NRFs.”
• Online Deep Learning: Growing RBM on the fly (2018, methodology): “We evaluate the OGD-RBM classifier, in comparison with the Support Vector Machine classifier (SVM), the Multi-layer Perceptron Neural Network (NN) classifier, the Classification Restricted Boltzmann Machine classifier (ClassRBM) [9] and the Scoring Table (ST) method on the three credit data sets (li”
• Generalized Autoencoder: A Neural Network Framework for Dimensionality Reduction (2014, background): “Classification restricted Boltzmann machine (ClassRBM) [7] may provide a solution to explicitly modeling class labels by fusing label vectors into the visible layer.”
• Deep learning for healthcare applications based on physiological signals: A review (2018, background): “Deep Belief Network (DBN) [45] and Restricted Boltzmann Machine (RBM) [48] are common forms of the deep generative model, where DBNs are stacked layers of RBM.”
• ApproxDBN: Approximate Computing for Discriminative Deep Belief Networks (2017, methodology): “Neural networks provide high performance for applications such as image recognition, text retrieval and pattern completion [1][2].”
• Deep Learning Face Representation from Predicting 10,000 Classes (2014, methodology): “Sun et al. [31] used multiple deep ConvNets to learn high-level face similarity features and trained classification RBM [22] for face verification.”
• Generative Adversarial Networks (2021, unknown): “The Restricted Boltzmann Machine [11] (RBM) and the Deep Belief Network [12] (DBN) are two prominent examples.”
• Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders (2015, methodology): “However, learning the parameters of the unsupervised architecture is quite difficult, often with little to no grasp of the final influence the generative parameters will have on the final discriminative model (Larochelle et al., 2012; Goodfellow et al., 2013).”