The rate adapting poisson model for information retrieval and object recognition

By Peter Gehler, Alex Holub, Max Welling. 2006

117 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science (2017, neutral): “…supervised training of deep arti ﬁ cial neural network architectures 42 , are also very successful as stand alone models in a variety of tasks, such as density estimation to model human choice 31 , collaborative ﬁ ltering 58 , information retrieval 59 , multi-class classi ﬁ cation 60 , and so on.”
Generating Multi-label Discrete Patient Records using Generative Adversarial Networks (2017, background): “There are studies that extend RBMs beyond binary variables (Hinton and Salakhutdinov, 2009; Gehler et al., 2006; Tran et al., 2011).”
Products of Experts (2007, methodology): “…ratecoded RBM to face recognition [10], the dual wing harmonium to video-track data [15], the rate adapting Poisson model (see figure 1) to text and image data [4], the product of HMMs model to language data [1], hierarchical versions of PoE to digits, text and collaborative filtering data [8] [9].”
Discovering Binary Codes for Documents by Learning Deep Generative Models (2011, methodology): “Several further developments of these undirected models (Gehler, Holub, & Welling, 2006; Xing, Yan, & Hauptmann, 2005) show that they are competitive in terms of retrieval accuracy to their directed counterparts.”
Two Distributed-State Models For Generating High-Dimensional Time Series (2011, methodology): “Keywords: unsupervised learning, restricted Boltzmann machines, time series, generative models, motion capture”
On the quantitative analysis of deep belief networks (2008, methodology): “RBM’s, and their generalizations to exponential family models, have been successfully applied in collaborative filtering (Salakhutdinov et al., 2007), informatio n and image retrieval ( Gehler et al., 2006 ), and time series modeling (Taylor et al., 2006).”
Neural Networks and Deep Learning (2018, unknown): “Advanced RBMs for topic modeling with a Poisson distribution are discussed in [134, 538].”
Replicated Softmax: an Undirected Topic Model (2009, methodology): “Several authors [ 4 , 17] used two-layer undirected graphical models, called Restricted Boltzmann Machines (RBMs), in which word-count vectors are modeled as a Poisson distribution.”
Semantic hashing (2009, methodology): “Several further developments of these undir ected models [6, 17] show that they are competitive in terms of retr ieval accuracy with their directed counterparts.”
Classification using discriminative restricted Boltzmann machines (2008, background): “image data (Gehler et al., 2006) or as a good initial training phase for deep neural network classifiers (Hinton, 2007).”
Learning Algorithms for the Classification Restricted Boltzmann Machine (2012, background): “Most of the time however, the features are learned while ignoring the target label information (Gehler et al., 2006; Xing et al., 2005).”
Bidirectional Helmholtz Machines (2015, background): “If the number of hidden units is small, this leads to low dimensional representations [112, 32, 91].”
Training restricted Boltzmann machines: An introduction (2014, background): “1 Introduction In the last years, models extending or borrowing concepts from restricted Boltzmann machines (RBMs, [49]) have enjoyed much popularity for pattern analysis and generation, with applications including image classification, processing, and generation [25, 51, 34, 28, 48, 31]; learning m”
A topological insight into restricted Boltzmann machines (2016, methodology): “Examples are density estimation to model human choice (Osogami and Otsuka, 2014), collaborative ﬁl-tering (Salakhutdinov et al, 2007), information retrieval (Gehler et al, 2006), or multi-class classiﬁcation (Larochelle and Bengio, 2008).”
Training restricted Boltzmann machines using approximations to the likelihood gradient (2008, methodology): “, 2006; Smolensky, 1986) are neural network models for unsupervised learning, but have recently seen a lot of application as feature extraction methods for supervised learning algorithms (Salakhutdinov et al., 2007; Larochelle et al., 2007; Bengio et al., 2007; Gehler et al., 2006; Hinton et al., 20”
Learning and Evaluating Boltzmann Machines (2008, methodology): “This will allow future application to models of real-valued data, such as image patches [18], or count data, such as word-count vectors of documents [ 3 ].”
Training Restricted Boltzmann Machines (2015, background): “, 2007); extraction of semantic document representations (Salakhutdinov and Hinton, 2009a; Gehler et al., 2006; Xing et al., 2005); and acoustic modeling (Mohamed and Hinton, 2010).”