Learning Deep Sigmoid Belief Networks with Data Augmentation

By Zhe Gan, Ricardo Henao, David Edwin Carlson, Lawrence Carin. 2015

111 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. Chunyuan Li
2. Zhe Gan
3. Yu Zhang
4. Lawrence Carin
5. Hao Wang
6. Dit-Yan Yeung
7. Changyou Chen
8. Qiang Yang

Citations in the corpus

• Nonlinear Statistical Learning with Truncated Gaussian Graphical Models (2016, background): “The restricted Boltzmann machine (RBM) (Hinton, 2002) and sigmoid belief network (SBN) (Neal, 1992; Gan et al., 2015), as well as the deep networks built upon them (Salakhutdinov & Hinton, 2009; Hinton et al.”
• Deep Temporal Sigmoid Belief Networks for Sequence Modeling (2015, background): “The proposed Temporal Sigmoid Belief Network (TSBN) model is a sequence of SBNs arranged in such way that at any given time step, the SBN’s biases depend on the state of the SBNs in the previous time steps.”
• One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay (2017, methodology): “Data augmentation techniques have been established to compensate for limited training data, in which random transformations are applied to the training examples in order to improve the diversity of the training samples [24].”
• Deep Poisson Factor Modeling (2015, background): “We compare our model (denoted DPFM) against LDA [3], FTM [29], RSM [12], nHDP [23] and DPFA with SBNs (DPFA-SBN) and RBMs (DPFA-RBM) [6].”
• A Survey on Bayesian Deep Learning (2016, methodology): “For the learning of h kn where l > 1, the same techniques as in [25] can be used.”
• Deep Generative Models for Relational Data with Side Information (2017, background): “Akin to the deep sigmoid belief-nets (Neal, 1992; Gan et al., 2015), we condition each node’s latent features in layer ` on its latent features in layer `+ 1 via a weight matrix W ∈ RK`×K`+1 (Fig.”
• Towards Better Representations with Deep/Bayesian Learning (2018, background): “…Chen et al., 2018a; Xu et al., 2017; Wang et al., 2017b; Pu et al., 2018b; Yuan et al., 2017, 2018; Chapfuwa et al., 2018), sigmoid belief networks (Gan et al., 2015b,c,a; Zhang et al., 2016a; Henao et al., 2015a), and their extensions to sequential data generation (Fan et al., 2016b; Zhang et…”
• Privacy Protection for Natural Language Records: Neural Generative Models for Releasing Synthetic Twitter Data (2016, methodology): “In this paper we use only redaction of handles and hashtags, since it can be argued that these comprise the large majority of identifying entities in Twitter data.2”