Online learning and generalization of parts-based image representations by non-negative sparse autoencoders

Neural Networks

Volumn 33, Issue , 2012, Pages 194-203

  Lemme, Andre ^a   Reinhart, René Felix ^a   Steil, Jochen Jakob ^a  

^a BIELEFELD UNIVERSITY   (Germany)

Author keywords

Autoencoder; Non negativity; Sparse coding

Indexed keywords

AUTOENCODERS; ENCODINGS; HANDWRITTEN DIGIT; IMAGE REPRESENTATIONS; MATRIX FACTORIZATIONS; NETWORK INITIALIZATION; NON-NEGATIVE SPARSE CODING; NON-NEGATIVITY; OFF-LINE ALGORITHM; ONLINE LEARNING; ONLINE LEARNING SCHEME; OVERFITTING; REAL-WORLD DATASETS; RECONSTRUCTION ERROR; SELF ADAPTATION; SPARSE CODING;

ENCODING (SYMBOLS);

LEARNING SYSTEMS;

ACCURACY; ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; AUTOENCODER; DATA BASE; IMAGE RECONSTRUCTION; MACHINE LEARNING; MATHEMATICAL COMPUTING; MATHEMATICAL PARAMETERS; OFFLINE ALGORITHM; ONLINE ANALYSIS; ONLINE LEARNING; ONLINE SYSTEM; PRIORITY JOURNAL; SYNAPSE;

ARTIFICIAL INTELLIGENCE; DATABASES, FACTUAL; FACE; HUMANS; IMAGE PROCESSING, COMPUTER-ASSISTED; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED; PHOTIC STIMULATION;

EID: 84863863720     PISSN: 08936080     EISSN: 18792782     Source Type: Journal    
DOI: 10.1016/j.neunet.2012.05.003     Document Type: Article

References (23)

1. Bax I., Heidemann G., Ritter H. Hierarchical feed-forward network for object detection tasks. Optical Engineering 2006, 45.
2. Bengio Y., Lamblin P., Popovici D., Larochelle H. Greedy layer-wise training of deep networks. NIPS 2007, 153-160.
3. Cao B. Detect and track latent factors with online nonnegative matrix factorization. Matrix 2007, 2689-2694.
4. Dornbusch, D., Haschke, R., Menzel, S., & Wersing, H. (2010). Correlating shape and functional properties using decomposition approaches. In Proceedings of the FLAIRS-23. (pp. 398-403).
5. Földiák P. Forming sparse representations by local anti-Hebbian learning. Biological Cybernetics 1990, 165-170.
6. Frank A. On Kuhn's Hungarian method-a tribute from Hungary. Naval Research Logistics 2005, 2-5.
7. Hinton G.E., Osindero S. A fast learning algorithm for deep belief nets. Neural Computation 2006, 1527-1554.
8. Hoyer P.O. Non-negative sparse coding. Neural Networks for Signal Processing 2002, XII:557-565.
9. Hoyer P.O. Non-negative matrix factorization with sparseness constraints. Machine Learning 2004, 1457-1469.
10. Larochelle H., Bengio Y., Louradour J., Lamblin P. Exploring strategies for training deep neural networks. Machine Learning 2009, 1-40.
11. Lee H., Ekanadham C., Ng A. Sparse deep belief net model for visual area V2. NIPS 2008, 873-880.
12. Lee D.D., Seung H.S. Learning the parts of objects by nonnegative matrix factorization. Nature 1999, 788-791.
13. Lemme, A., Reinhart, R.F., & Steil, J.J. (2010). Efficient online learning of a non-negative sparse autoencoder. In Proceedings of the ESANN. (pp. 1-6).
14. Mairal J., Bach F., Ponce J., Sapiro G. Online learning for matrix factorization and sparse coding. Machine Learning 2010, 19-60.
15. Olshausen B., Field D. Sparse coding of sensory inputs. Current Opinion in Neurobiology 2004, 481-487.
16. Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions On Systems Man And Cybernetics 1979, 62-66.
17. Ranzato M., Boureau Y.-L., LeCun Y. Sparse feature learning for deep belief networks. NIPS 2008, 1185-1192.
18. Shastri B., Levine M. Face recognition using localized features based on non-negative sparse coding. Machine Vision and Applications 2007, 107-122.
19. Spratling M. Learning image components for object recognition. Machine Learning 2006, 793-815.
20. Steil, J.J. (2004). Backpropagation-decorrelation: online recurrent learning with O(N) complexity. In Proceedings of the IJCNN. (pp. 843-848).
21. Tanaka K. Columns for complex visual object features in the inferotemporal cortex: clustering of cells with similar but slightly different stimulus selectivities. Cerebral Cortex 2003, 90-99.
22. Triesch J. A gradient rule for the plasticity of a neuron's intrinsic excitability. Neural Computation 2005, 65-70.
23. Wersing H., Körner E. Learning optimized features for hierarchical models of invariant object recognition. Neural Computation 2003, 1559-1588.