Training products of experts by minimizing contrastive divergence

作者: Geoffrey E. Hinton

DOI: 10.1162/089976602760128018

关键词: Deep belief networkConditional independenceMachine learningProduct of expertsProbability distributionMathematicsData typeBoltzmann machineInferenceArtificial intelligenceLatent variable

摘要: It is possible to combine multiple latent-variable models of the same data by multiplying their probability distributions together and then renormalizing. This way of combining individual “…

参考文章(23)
Geoffrey E. Hinton, Andrew D. Brown, Products of Hidden Markov Models. international conference on artificial intelligence and statistics. ,(2001)
Patrick H. Winston, Learning Structural Descriptions From Examples The Psychology of Computer Vision. ,(1970)
T. J. Sejnowski, G. E. Hinton, Learning and relearning in Boltzmann machines Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. pp. 282- 317 ,(1986)
David E. Rumelhart, James L. McClelland, , Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations Computational Models of Cognition and Perception. ,(1986) , 10.7551/MITPRESS/5236.001.0001
P. Smolensky, Information processing in dynamical systems: foundations of harmony theory Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. pp. 194- 281 ,(1986)
Patrick Henry Winston, The psychology of computer vision Pattern Recognition. ,vol. 8, pp. 193- ,(1976) , 10.1016/0031-3203(76)90020-0
G. Hinton, P Dayan, B. Frey, R. Neal, The "Wake-Sleep" Algorithm for Unsupervised Neural Networks Science. ,vol. 268, pp. 1158- 1161 ,(1995) , 10.1126/SCIENCE.7761831
Stuart Geman, Donald Geman, Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-6, pp. 721- 741 ,(1984) , 10.1109/TPAMI.1984.4767596
M. Revow, C.K.I. Williams, G.E. Hinton, Using generative models for handwritten digit recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 18, pp. 592- 606 ,(1996) , 10.1109/34.506410