Stable and efficient representation learning with nonnegativity constraints

31st International Conference on Machine Learning, ICML 2014

Volumn 4, Issue , 2014, Pages 3127-3135

  Lin, Tsung Han ^a   Kung, H T ^a  

^a HARVARD UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

APPROXIMATION ALGORITHMS; ARTIFICIAL INTELLIGENCE; CLASSIFICATION (OF INFORMATION); IMAGE MATCHING; LEARNING SYSTEMS;

CLASSIFICATION ACCURACY; DEEP ARCHITECTURES; EFFICIENT APPROXIMATION ALGORITHMS; LEARNING FRAMEWORKS; NON-NEGATIVITY CONSTRAINTS; ORTHOGONAL MATCHING PURSUIT; SPARSE REPRESENTATION; SUPERVISED CLASSIFIERS;

IMAGE CLASSIFICATION;

EID: 84919800661     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (32)

1. Bengio, Y., Courville, A., and Vincent, P. Representation learning: A review and new perspectives. IEEE Trans. Pattern Anal. Machine Intell., 35(8): 1798-1828, 2013.
2. Berkes, P. and Wiskott, L. Slow feature analysis yields a rich repertoire of complex cell properties. Journal of Vision, 5(6):579-602, 2005.
3. Bo, L., Ren, X., and Fox, D. Unsupervised feature learning for RGB-D based object recognition. In ISER, 2012.
4. Bruckstein, A., Elad, M., and Zibulevsky, M. On the uniqueness of nonnegative sparse solutions to underde- Termined systems of equations. IEEE Trans. Inform. Theory, 54(11):4813-4820, 2008.
5. Coates, A. and Ng, A. The importance of encoding versus training with sparse coding and vector quantization. In ICML, 2011a.
6. Coates, A. and Ng, A. Selecting receptive fields in deep networks. In NIPS, 2011b.
7. Coates, A., Ng, A., and Lee, H. An analysis of single-layer networks in unsupervised feature learning. In AISTATS, 2011.
8. Donoho, D. and Stodden, V. When does non-negative matrix factorization give a correct decomposition into parts? In NIPS. 2003.
9. Donoho, D., Elad, M., and Temlyakov, V. Stable recovery of sparse overcomplete representations in the presence of noise. IEEE Trans. Inform. Theory, 52(1):6-18, 2006.
10. Goodfellow, I, Courville, A, and Bengio, Y. Large-scale feature learning with spike-and-slab sparse coding. In ICML, 2012.
11. Goodfellow, I., Warde-Farley, D., and Mirza, M. Maxout Networks. In ICML, 2013.
12. Gregor, K. and LeCun, Y. Learning fast approximations of sparse coding. In ICML, 2010.
13. Hoyer, P. Modeling receptive fields with non-negative sparse coding. Neurocomputing, 52:547-552, 2003.
14. Hoyer, P. Non-negative matrix factorization with sparse- ness constraints. The Journal of Machine Learning Research, 5:1457-1469, 2004.
15. Hui, K.-Y. Direct Modeling of Complex Invariances for Visual Object Features. In ICML, 2013.
16. Kavukcuoglu, K., Ranzato, M., and LeCun, Y. Fast inference in sparse coding algorithms with applications to object recognition. CBLL-TR-2008-12-01, NYU, 2008.
17. Kavukcuoglu, K., Sermanet, P., Boureau, Y-L., Gregor, K., Mathieu, M., and LeCun, Y. Learning convolutional feature hierarchies for visual recognition. In NIPS, 2010.
18. Krizhevsky, A. and Hinton, G. E. Learning multiple layers of features from tiny images. Technical report, University of Toronto, 2009.
19. Lee, D. D. and Seung, H. S. Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755): 788-791, 1999.
20. Lee, H., Battle, A., Raina, R., and Ng, A. Efficient sparse coding algorithms. In NIPS, 2006.
21. Lee, H., Grosse, R., Ranganath, R., and Ng, A. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. In ICML, 2009.
22. Nair, V. and Hinton, G. E. Rectified linear units improve restricted boltzmann machines. In ICML, 2010.
23. Ngiam, J., Koh, P.-W., Chen, Z., Bhaskar, S., and Ng, A. Sparse filtering. In NIPS, 2011.
24. Paatero, P. and Tapper, U. Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values. Environmetrics, 5(2): 111 126, 1994.
25. Pati, Y. C., Rezaiifar, R., and Krishnaprasad, P. S. Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition. In Asilomar Conference on Signals, Systems and Computers. IEEE, 1993.
26. Raina, R., Battle, A., Lee, H., Packer, B., and Ng, A. Self- Taught learning: Transfer learning from unlabeled data. In ICML, 2007.
27. Ranzato, M., Huang, F., Boureau, Y-L., and Lecun, Y. Unsupervised learning of invariant feature hierarchies with applications to object recognition. In CVPR. IEEE, 2007.
28. Rozell, C., Johnson, D., Baraniuk, R., and Olshausen, B. A. Sparse coding via thresholding and local competition in neural circuits. Neural computation, 20(10):2526-2563, 2008.
29. Rubinstein, R., Zibulevsky, M., and Elad, M. Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit. CS Technion, 2008.
30. Sindhwani, V. and Ghoting, A. Large-scale distributed non- negative sparse coding and sparse dictionary learning. In KDD, 2012.
31. Slawski, M. and Hein, M. Sparse recovery by thresholded non-negative least squares. In NIPS, 2011.
32. Zeiler, M. and Fergus, R. Stochastic pooling for regulariza- Tion of deep convolutional neural networks. ICLR, 2013.