Computational Intelligence and Neuroscience
Volume 2009 (2009), Article ID 381457, 19 pages
doi:10.1155/2009/381457
Research Article

Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation

M. W. Spratling,1,2 K. De Meyer,1,2 and R. Kompass3

1Division of Engineering, King's College London, London WC2R 2LS, UK
2Centre for Brain and Cognitive Development, Birkbeck College, University of London, London WC1E 7HX, UK
3Artificial Intelligence Group, Institute of Computer Science, Freie Universität Berlin, 14195 Berlin, Germany

Received 27 August 2008; Accepted 7 February 2009

Academic Editor: Seungjin Choi

Copyright © 2009 M. W. Spratling et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Linked References

  1. T. Feng, S. Z. Li, H.-Y. Shum, and H. Zhang, “Local non-negative matrix factorization as a visual representation,” in Proceedings of the 2nd International Conference on Development and Learning (ICDL '02), pp. 178–186, Cambridge, Mass, USA, June 2002. View at Publisher · View at Google Scholar
  2. P. O. Hoyer, “Non-negative sparse coding,” in Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing (NNSP '02), pp. 557–565, Martigny, Switzerland, September 2002. View at Publisher · View at Google Scholar
  3. P. O. Hoyer, “Non-negative matrix factorization with sparseness constraints,” The Journal of Machine Learning Research, vol. 5, pp. 1457–1469, 2004.
  4. D. D. Lee and H. S. Seung, “Learning the parts of objects by non-negative matrix factorization,” Nature, vol. 401, no. 6755, pp. 788–791, 1999. View at Publisher · View at Google Scholar · View at PubMed
  5. S. Z. Li, X. W. Hou, H. J. Zhang, and Q. S. Cheng, “Learning spatially localized, parts-based representation,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR '01), vol. 1, pp. 207–212, Kauai, Hawaii, USA, December 2001. View at Publisher · View at Google Scholar
  6. W. Liu and N. Zheng, “Non-negative matrix factorization based methods for object recognition,” Pattern Recognition Letters, vol. 25, no. 8, pp. 893–897, 2004. View at Publisher · View at Google Scholar
  7. W. Liu, N. Zheng, and X. Lu, “Non-negative matrix factorization for visual coding,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '03), vol. 3, pp. 293–296, Hong Kong, April 2003. View at Publisher · View at Google Scholar
  8. M. W. Spratling, “Learning image components for object recognition,” Journal of Machine Learning Research, vol. 7, pp. 793–815, 2006.
  9. R. Kompass, “A generalized divergence measure for nonnegative matrix factorization,” Neural Computation, vol. 19, no. 3, pp. 780–791, 2007. View at Publisher · View at Google Scholar · View at PubMed · View at MathSciNet
  10. M. W. Spratling, “Pre-synaptic lateral inhibition provides a better architecture for self-organizing neural networks,” Network: Computation in Neural Systems, vol. 10, no. 4, pp. 285–301, 1999. View at Publisher · View at Google Scholar
  11. M. W. Spratling and M. H. Johnson, “Dendritic inhibition enhances neural coding properties,” Cerebral Cortex, vol. 11, no. 12, pp. 1144–1149, 2001. View at Publisher · View at Google Scholar
  12. M. W. Spratling and M. H. Johnson, “Preintegration lateral inhibition enhances unsupervised learning,” Neural Computation, vol. 14, no. 9, pp. 2157–2179, 2002. View at Publisher · View at Google Scholar · View at PubMed
  13. D. Charles and C. Fyfe, “Discovering independent sources with an adapted PCA neural network,” in Proceedings of the 2nd International ICSC Symposium on Soft Computing (SOCO '97), D. W. Pearson, Ed., NAISO Academic Press, Nîmes, France, September 1997.
  14. D. Charles and C. Fyfe, “Modelling multiple-cause structure using rectification constraints,” Network: Computation in Neural Systems, vol. 9, no. 2, pp. 167–182, 1998. View at Publisher · View at Google Scholar
  15. D. Charles, C. Fyfe, D. McDonald, and J. Koetsier, “Unsupervised neural networks for the identification of minimum overcomplete basis in visual data,” Neurocomputing, vol. 47, pp. 119–143, 2002. View at Publisher · View at Google Scholar
  16. C. Fyfe, “A neural network for PCA and beyond,” Neural Processing Letters, vol. 6, no. 1-2, pp. 33–41, 1997. View at Publisher · View at Google Scholar
  17. G. F. Harpur, Low entropy coding with unsupervised neural networks, Ph. D. thesis, Department of Engineering, University of Cambridge, Cambridge, UK, 1997.
  18. G. F. Harpur and R. W. Prager, “A fast method for activating competitive self-organising neural networks,” in Proceedings of the International Symposium on Artificial Neural Networks (ISANN '94), pp. 412–418, Taipei, Taiwan, December 1994.
  19. G. E. Hinton, P. Dayan, B. J. Frey, and R. M. Neal, “The “wake-sleep” algorithm for unsupervised neural networks,” Science, vol. 268, no. 5214, pp. 1158–1161, 1995. View at Publisher · View at Google Scholar
  20. G. F. Harpur and R. W. Prager, “Development of low entropy coding in a recurrent network,” Network: Computation in Neural Systems, vol. 7, no. 2, pp. 277–284, 1996. View at Publisher · View at Google Scholar · View at PubMed
  21. D. D. Lee and H. S. Seung, “Algorithms for non-negative matrix factorization,” in Advances in Neural Information Processing Systems 13, T. K. Leen, T. G. Dietterich, and V. Tresp, Eds., pp. 556–562, MIT Press, Cambridge, Mass, USA, 2001.
  22. D. Kersten, P. Mamassian, and A. Yuille, “Object perception as Bayesian inference,” Annual Review of Psychology, vol. 55, no. 1, pp. 271–304, 2004. View at Publisher · View at Google Scholar · View at PubMed
  23. A. Yuille and D. Kersten, “Vision as Bayesian inference: analysis by synthesis?,” Trends in Cognitive Sciences, vol. 10, no. 7, pp. 301–308, 2006. View at Publisher · View at Google Scholar · View at PubMed
  24. P. Földiák, “Forming sparse representations by local anti-Hebbian learning,” Biological Cybernetics, vol. 64, no. 2, pp. 165–170, 1990. View at Publisher · View at Google Scholar
  25. G. E. Hinton and Z. Ghahramani, “Generative models for discovering sparse distributed representations,” Philosophical Transactions of the Royal Society B, vol. 352, no. 1358, pp. 1177–1190, 1997. View at Publisher · View at Google Scholar · View at PubMed
  26. A. Cichocki and R. Zdunek, “Multilayer nonnegative matrix factorization using projected gradient approaches,” International Journal of Neural Systems, vol. 17, no. 6, pp. 431–446, 2007. View at Publisher · View at Google Scholar
  27. D. Soukup and I. Bajla, “Robust object recognition under partial occlusions using NMF,” Computational Intelligence and Neuroscience, vol. 2008, Article ID 857453, 14 pages, 2008. View at Publisher · View at Google Scholar · View at PubMed
  28. M. W. Spratling and M. H. Johnson, “Exploring the functional significance of dendritic inhibition in cortical pyramidal cells,” Neurocomputing, vol. 52–54, pp. 389–395, 2003. View at Publisher · View at Google Scholar