Learning and Selecting Features Jointly with Point-wise Gated Boltzmann Machines

By Kihyuk Sohn, Guanyu Zhou, Chansoo Lee, Honglak Lee. 2013

102 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.

Citations in the corpus

A Hybrid Differential Evolution Approach to Designing Deep Convolutional Neural Networks for Image Classification (2018, neutral): “Therefore, they are picked as the peer competitors of the proposed algorithm, which are CAE-2 [13], TIRBM [15], PGBM+DN1 [5], ScatNet-2 [2], RandNet-2 [3], PCANet-2 (softmax) [3], LDANet-2 [3], SVM+RBF [8], SVM+Poly [8], NNet [8], SAA-3 [8] and DBN-3 [8].”
Tagger: Deep Unsupervised Perceptual Grouping (2016, background): “Many of the works in that area [14, 29, 27, 11] build upon Restricted Boltzmann Machines.”
Deep Learning of Representations: Looking Forward (2013, methodology): “ltiplicative interactions between the factors (Tenenbaum and Freeman, 2000; Desjardins et al., 2012) or orthogonality of the features derivative with respect to the input (Rifai et al., 2011b, 2012a; Sohn et al., 2013). The parametrization and training procedure may also be used to disentangle discr”
Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification (2016, background): “Several attempts (e.g., Ranzato & Szummer (2008); Larochelle & Bengio (2008); Sohn et al. (2013); Goodfel-low et al. (2013)) had been made to couple the unsupervised and supervised learning in the same phase, making unsupervised objectives able to impact the network training after supervised…”
Learning in high-dimensional multimedia data: the state of the art (2015, background): “The focus of feature selection is to select a subset of variables from the input which can efficiently describe the input data while reducing effects from noise or irrelevant variables and still provide good prediction results [26,78,42].”
Minerva: A Scalable and Highly Efficient Training Platform for Deep Learning (2014, background): “, inputfiles[1]); for(int n = 1; n < numBatchFiles; ++n) { nextBatch = LoadBatches(.”
Learning to Disentangle Factors of Variation with Manifold Interaction (2014, background): “The point-wise gated Boltzmann machine (Sohn et al., 2013) is an instance of a higher-order Boltzmann machine that jointly learns and selects task-relevant features.”
Look and Think Twice: Capturing Top-Down Visual Attention with Feedback Convolutional Neural Networks (2015, background): “Deep Boltzmman Machines (DBM) [23, 26] and Deconvolutional Nerual Networks [34] try to formulate”
Evolving Deep Convolutional Neural Networks for Image Classification (2017, unknown): “The peer competitors on other benchmarks are CAE-2 [47], TIRBM [48], 1https://github.com/zalandoresearch/fashion-mnist PGBM+DN-1 [49], ScatNet-2 [50], RandNet-2 [51], PCANet-2 (softmax) [51], LDANet-2 [51], SVM+RBF [44], SVM+Poly [44], NNet [44], SAA-3 [44], and DBN-3 [44], which are from [51] recen”
Deep Representation Learning with Target Coding (2015, methodology): “com) (4)This MNIST variant corresponds to the challenging mnist-rotback-image reported in (Rifai et al. 2011; Sohn et al. 2013; Vincent et al. 2010).”
Combining multiple sources of knowledge in deep CNNs for action recognition (2016, background): “[20] proposed a point-wise gated boltz-mann machine (PGBM) that can distinguish task-relevant features from distracting task-irrelevant features by introducing switching units that have multiplicative interactions between visible and hidden units.”
A Review of Deep Learning Models for Time Series Prediction (2019, background): “RBM has several extensions, e.g., conditional RBM [162], gated RBM [163], etc.”
User Conditional Hashtag Prediction for Images (2015, methodology): “Multiplicative three-way connections have been used as a feature gating mechanism in restricted Boltzmann machines [15, 20, 9, 14].”
Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification (2018, background): “To be specific, the peer competitors on the three benchmarks are CAE-2 [21], TIRBM [22], PGBM+DN1 [23], ScatNet-2 [25], RandNet-2 [24], PCANet-2 (softmax) [24], LDANet-2 [24], SVM+RBF [20], SVM+Poly [20], NNet [20], SAA-3 [20] and DBN-3 [20], which are from the literature [24] recently published and”