Training restricted Boltzmann machines using approximations to the likelihood gradient

Keywords

Divergence (linguistics), Boltzmann machine, Computer science, Algorithm, Simple (philosophy)

References

• On Contrastive Divergence LearningMiguel Á. Carreira-Perpiñán, Geoffrey E. Hinton — 2005
• On the Statistical Analysis of Dirty PicturesJulian Besag — 1986
• Information processing in dynamical systems: foundations of harmony theoryPaul Smolensky — 1986
• On the convergence of markovian stochastic algorithms with rapidly decreasing ergodicity ratesLaurent Younès — 1999
• An empirical evaluation of deep architectures on problems with many factors of variationHugo Larochelle, Dumitru Erhan, Aaron Courville — 2007
• A Stochastic Approximation MethodHerbert Robbins, Sutton Monro — 1951
• The rate adapting poisson model for information retrieval and object recognitionPeter Gehler, Alex Holub, Max Welling — 2006
• Connectionist Learning of Belief NetworksRadford M. Neal — 1992
• On the quantitative analysis of deep belief networksRuslan Salakhutdinov, Iain Murray — 2008
• Restricted Boltzmann machines for collaborative filteringRuslan Salakhutdinov, Andriy Mnih, Geoffrey E. Hinton — 2007
• Training Products of Experts by Minimizing Contrastive DivergenceGeoffrey E. Hinton — 2002
• Graphical Models, Exponential Families, and Variational InferenceMartin J. Wainwright, Michael I. Jordan — 2008
• Exponential Family Harmoniums with an Application to Information RetrievalMax Welling, Michal Rosen‐Zvi, Geoffrey E. Hinton — 2004
• A Fast Learning Algorithm for Deep Belief NetsGeoffrey E. Hinton, Simon Osindero, Yee‐Whye Teh — 2006
• Justifying and Generalizing Contrastive DivergenceYoshua Bengio, Olivier Delalleau — 2009
• Combining Top-Down and Bottom-Up SegmentationEran Borenstein, E. Sharon, Shimon Ullman — 2004
• A New Learning Algorithm for Mean Field Boltzmann MachinesMax Welling, Hinton, GE — 2002
• The Convergence of Contrastive DivergencesAlan Yuille — 2004
• Reducing the Dimensionality of Data with Neural NetworksGeoffrey E. Hinton, Ruslan Salakhutdinov — 2006
• The mnist database of handwritten digitsYann LeCun, Corinna Cortes — 2005

Cited by

• Epistemological Databases for Probabilistic Knowledge Base ConstructionMichael Wick — 2015
• Deep Modeling of Group Preferences for Group-Based RecommendationLiang Hu, Jian Cao, Guandong Xu — 2014
• GPU implementation of a deep learning network for image recognition tasksSean Patrick Parker — 2012
• Unsupervised Feature Learning and Deep Learning: A Review and New PerspectivesYoshua Bengio, Aaron Courville, Pascal Vincent — 2012
• Two Distributed-State Models For Generating High-Dimensional Time SeriesGraham W. Taylor, Geoffrey E. Hinton, Sam T. Roweis — 2011
• Learned Factorization Models to Explain Variability in Natural Image SequencesBenjamin J. Culpepper — 2011
• Particle Filtered MCMC-MLE with Connections to Contrastive DivergenceArthur Asuncion, Qiang Liu, Alexander Ihler — 2010
• Learning Deep Boltzmann Machines using Adaptive MCMCRuslan Salakhutdinov — 2010
• Multimodal learning with deep Boltzmann machinesNitish Srivastava, Ruslan Salakhutdinov — 2012
• Multiple Testing under Dependence via Semiparametric Graphical ModelsJie Liu, Chunming Zhang, Elizabeth S. Burnside — 2014
• DETONATION CLASSIFICATION FROM ACOUSTIC SIGNATURE WITH THE RESTRICTED BOLTZMANN MACHINEYoshua Bengio, Nicolas Chapados, Olivier Delalleau — 2012
• Deep Boltzmann MachinesRuslan Salakhutdinov, Geoffrey E. Hinton — 2009
• Tempered Markov Chain Monte Carlo for training of Restricted Boltzmann MachinesGuillaume Desjardins, Aaron Courville, Yoshua Bengio — 2010
• Training Restricted Boltzmann MachinesAsja Fischer — 2015
• SampleRank: Training Factor Graphs with Atomic GradientsKhashayar Rohanimanesh, Kedar Bellare, Aron Culotta — 2011
• Deep Boltzmann Machines as Hierarchical Generative Models of Perceptual Inference in the CortexDavid Reichert — 2012
• Classification of medical data using Restricted Boltzmann MachinesMarkku K. Aalto — 2014
• Modeling time-series with deep networksMartin Längkvist — 2014
• Deep learning of representations and its application to computer visionIan Goodfellow — 2015
• Learning Deep Representations : Toward a better new understanding of the deep learning paradigm. (Apprentissage de représentations profondes : vers une meilleure compréhension du paradigme d'apprentissage profond)Ludovic Arnold — 2013

Related papers

• Rademacher Complexity of the Restricted Boltzmann MachineXiao Zhang — 2015
• Approximate Learning Algorithm for Restricted Boltzmann MachinesMuneki Yasuda, Kazuyuki Tanaka — 2008
• Boltzmann Machines with Identified StatesMasashi Kobayashi — 2008
• Higher‐order Boltzmann machinesTerrence J. Sejnowski — 1987
• Universal Approximation Results for the Temporal Restricted Boltzmann Machine and the Recurrent Temporal Restricted Boltzmann MachineSimon Odense, Roderick Edwards — 2016
• An Overview of Restricted Boltzmann MachinesVidyadhar Upadhya, P. S. Sastry — 2019
• Boltzmann machines as two-dimensional tensor networksSujie Li, Feng Pan, Pengfei Zhou — 2021
• Two new classes of Boltzmann machinesYing Liu — 1993
• Global Optimization Using Meta-Controlled Boltzmann MachineShamshul Bahar Yaakob, Junzo Watada — 2010