Exploiting local structure in Boltzmann machines

Neurocomputing

Volumn 74, Issue 9, 2011, Pages 1411-1417

  Schulz, Hannes ^a   Müller, Andreas ^a   Behnke, Sven ^a  

^a UNIVERSITY OF BONN   (Germany)

Author keywords

Generative models; Low level vision; Restricted Boltzmann machines

Indexed keywords

BOLTZMANN MACHINES; GENERATIVE MODEL; HIDDEN VARIABLE; IMAGE DATA; IMAGE STATISTICS; LATERAL INTERACTIONS; LOCAL STRUCTURE; LONG-RANGE DEPENDENCIES; LOW-LEVEL VISION; RESTRICTED BOLTZMANN MACHINE; RESTRICTED BOLTZMANN MACHINES;

ARTICLE; ARTIFICIAL NEURAL NETWORK; CLASSIFICATION ALGORITHM; CONTROLLED STUDY; DISCRIMINATION LEARNING; IMAGE ANALYSIS; IMAGE RECONSTRUCTION; INTERMETHOD COMPARISON; LEARNING ALGORITHM; MACHINE LEARNING; MATHEMATICAL MODEL; PRIORITY JOURNAL; QUALITATIVE ANALYSIS; RESTRICTED BOLTZMANN MACHINE;

EID: 79953035087     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2010.12.014     Document Type: Article

References (18)

1. Smolensky P. Information processing in dynamical systems: foundations of harmony theory. Parallel Distributed Processing, Chapter 6 1986, vol. 1:194-281. MIT Press, Cambridge.
2. Hinton G., Osindero S., Teh W. A fast learning algorithm for deep belief nets. Neural Computation 2006, 18(7):1527-1554.
3. Hinton G. Training products of experts by minimizing contrastive divergence. Neural Computation 2002, 14(8):1771-1800.
4. J. Huang, D. Mumford, Statistics of natural images and models, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1999, pp. 1541-1547.
5. Osindero S., Hinton G. Modeling image patches with a directed hierarchy of Markov random fields. Advances in Neural Information Processing Systems (NIPS) 2008, 20:1121-1128.
6. M. Welling, G. Hinton, S. Osindero, Learning sparse topographic representations with products of student-t distributions, in: Advances in Neural Information Processing Systems (NIPS), 2002, pp. 1359-1366.
7. Roth S., Black M. Fields of experts. International Journal of Computer Vision IJCV 2009, 82(2):205-229.
8. Hyvärinen A., Hoyer P. A two-layer sparse coding model learns simple and complex cell receptive fields and topography from natural images. Journal on Vision Research 2001, 41(18):2413-2423.
9. LeCun Y., Bottou L., Bengio Y., Haffner P. Gradient-based learning applied to document recognition. Proceedings of the IEEE 1998, 86(11):2278-2324.
10. Bengio Y., Lamblin P., Popovici D., Larochelle H. Greedy layer-wise training of deep networks. Advances in Neural Information Processing Systems (NIPS) 2008, 20:841-848.
11. Behnke S. Hierarchical Neural Networks for Image Interpretation 2003, Springer-Verlag.
12. H. Lee, R. Grosse, R. Ranganath, Y. Ng, Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, in: International Conference on Machine Learning (ICML), 2009, p. 77.
13. Norouzi M., Ranjbar M., Mori G. Stacks of convolutional restricted Boltzmann machines for shift-invariant feature learning. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2009, 2735-2742. IEEE.
14. R. Salakhutdinov, Learning deep generative models. Ph.D. Thesis, University of Toronto, 2009.
15. R. Salakhutdinov, Learning and evaluating Boltzmann machines. Technical Report, University of Toronto, 2008.
16. T. Tieleman, Training restricted Boltzmann machines using approximations to the likelihood gradient, in: International Conference on Machine Learning (ICML), 2008, pp. 1064-1071.
17. R. Salakhutdinov, G. Hinton, Deep Boltzmann machines, in: Proceedings of Conference on Artificial Intelligence and Statistics, vol. 5, 2009, pp. 448-455.
18. R. Uetz, S. Behnke, Large-scale object recognition with CUDA-accelerated hierarchical neural networks, in: Proceedings of the IEEE International Conference on Intelligent Computing and Intelligent Systems, 2009.