Training Products of Experts by Minimizing Contrastive Divergence

Keywords

Latent variable, Divergence (linguistics), Inference, Computer science, Artificial intelligence

References

• Products of Hidden Markov ModelsAndrew D. Brown, Geoffrey E. Hinton — 2001
• Learning structural descriptions from examplesPatrick Henry Winston — 1970
• Credal Networks under Maximum EntropyThomas Lukasiewicz — 2000
• Information processing in dynamical systems: foundations of harmony theoryPaul Smolensky — 1986
• The psychology of computer visionPatrick Henry Winston — 1976
• The "wake-sleep" algorithm for unsupervised neural networks.Geoffrey E. Hinton, Peter Dayan, Brendan J. Frey — 1995
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesStuart Geman, Donald Geman — 1984
• Unsupervised learning of distributionsPeter Reimann — 1997
• Combining Probability Distributions: A Critique and an Annotated BibliographyChristian Genest, James V. Zidek — 1986
• Using Generative Models for Handwritten Digit RecognitionMichael Revow, Christopher K. I. Williams, Geoffrey E. Hinton — 1996
• Connectionist Learning of Belief NetworksRadford M. Neal — 1992
• Bias/Variance Decompositions for Likelihood-Based EstimatorsTom Heskes — 1998
• A Maximum Entropy Approach to Natural Language ProcessingAdam Berger, Vincent J. Della Pietra, Stephen A. Della Pietra — 1996
• Recognizing Hand-written Digits Using Hierarchical Products of ExpertsGuy Mayraz, Geoffrey E. Hinton — 2002
• A Gradient-Based Boosting Algorithm for Regression ProblemsRichard S. Zemel, Toniann Pitassi — 2000
• Biologically Plausible Error-Driven Learning Using Local Activation Differences: The Generalized Recirculation AlgorithmRandall C. O’Reilly — 1996
• Rate-coded Restricted Boltzmann Machines for Face RecognitionYee Whye Teh, Geoffrey E. Hinton — 2000
• Learning Continuous Attractors in Recurrent NetworksH. Sebastian Seung — 1997
• Learning Representations by RecirculationGeoffrey E. Hinton, James L. McClelland — 1987
• Attractor Dynamics in Feedforward Neural NetworksLawrence K. Saul, Michael I. Jordan — 2000

Cited by

• Scalability of using Restricted Boltzmann Machines for combinatorial optimizationMalte Probst, Franz Rothlauf, Jörn Grahl — 2014
• Epistemological Databases for Probabilistic Knowledge Base ConstructionMichael Wick — 2015
• A hierarchy of recurrent networks for speech recognitionBenjamin Schrauwen, Lars Buesing — 2009
• Complex cell pooling and the statistics of natural imagesYingbin Xiao, Yingbin Xiao — 2007
• Structure Learning in Sequential DataLiam Stewart — 2005
• DNdisorder: predicting protein disorder using boosting and deep networksJesse Eickholt, Jianlin Cheng — 2013
• Value and reward based learning in neurorobotsWarren Robert — 2013
• Learning Document Semantic Representation with Hybrid Deep Belief NetworkJosé Luis Segovia Bernabé — 2015
• Event Recognition Based on Deep Learning in Chinese Texts航太 渡辺, 芳昭 戸山, 守雄 松本 — 2016
• Incorporating Boltzmann Machine Priors for Semantic Labeling in Images and VideosAndrew Kae — 2014
• A Learning Framework for Winner-Take-All Networks with Stochastic SynapsesB. U. Musa, Wah Hoon Siew, M.D. Judd — 2017
• Fast Maximum Likelihood Estimation via Equilibrium Expectation for Large Network DataMaksym Byshkin, Alex Stivala, Antonietta Mira — 2018
• An Adaptive Markov Random Field for Structured Compressive SensingCarlos Pineda — 2018
• eToxPred: a machine learning-based approach to estimate the toxicity of drug candidatesJosé Antonio Fernández Ordóñez — 2019
• Semisupervised Deep Stacking Network with Adaptive Learning Rate Strategy for Motor Imagery EEG Recognition茅佳妮 — 2019
• Snuba: Automating Weak Supervision to Label Training DataХанхареев Сергей Степанович, Амагзаева Галина Сергеевна, Гаднаева Людмила Александровна — 2018
• IBAL: A Probabilistic Rational Programming LanguageAvi Pfeffer — 2001
• Image Modeling Using Tree Structured Conditional Random FieldsPranjal Awasthi, Aakanksha Gagrani, Balaraman Ravindran — 2007
• Graphical Models and Overlay Networks for Reasoning about Large Distributed SystemsCentral South University National Clinical Research Center For Geriatric Disorders Xiangya Hospital, Joint Surgery Branch Of The Chinese Orthopedic Association — 2010
• Hierarchical Probabilistic Neural Network Language ModelFréderic Morin, Yoshua Bengio — 2005

Related papers

• PROPCNSREG: Stata module fitting a measurement model with causal indicatorsMaarten L. Buis — 2013
• A latent-observed dissimilarity measureYasushi Terazono — 2016
• Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and LearningChristopher Zach, Huu Le — 2020
• Variational Inference for Integrated Choice and Latent Variable (Iclv) Models: Independence from the Number of Latent Variables and Choice OptionsGyeongjun Kim, Yeseul Kang, Keemin Sohn — 2023
• Variational f-divergence MinimizationMing‐Tian Zhang, Thomas Bird, Raza Habib — 2019
• Three models for combining information from causal indicatorsMaarten L. Buis — 2009
• Cycle-Consistent Adversarial Learning as Approximate Bayesian InferenceLouis C. Tiao, Edwin V. Bonilla, Fábio Ramos — 2018