Unsupervised neural networks for the identification of minimum overcomplete basis in visual data

Neurocomputing

Volumn 47, Issue 1-4, 2002, Pages 119-143

  Charles, Darryl ^a   Fyfe, Colin ^a   McDonald, Donald ^a   Koetsier, Jos ^a  

^a UNIVERSITY OF THE WEST OF SCOTLAND   (United Kingdom)

Author keywords

Multiple cause; Sparse code; Unsupervised

Indexed keywords

CODES (SYMBOLS); FUNCTIONS; GAUSSIAN NOISE (ELECTRONIC); IDENTIFICATION (CONTROL SYSTEMS); VECTORS;

ENERGY FUNCTION;

NEURAL NETWORKS;

ARTIFICIAL NEURAL NETWORK; CODING; DATA BASE; IMAGE ANALYSIS; MATHEMATICAL COMPUTING; METHODOLOGY; NOISE STANDARD; NONLINEAR SYSTEM; NORMAL DISTRIBUTION; PRINCIPAL COMPONENT ANALYSIS; PRIORITY JOURNAL; REVIEW; VISUAL INFORMATION;

EID: 0036707219     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(01)00583-5     Document Type: Review

References (27)

1. H.B. Barlow, T. Kaushal, G. Mitchison, Finding minimum entropy codes, Neural Comput. 1 (1989) 412-423.
2. C.M. Bishop, Curvature-driven smoothing in backpropagation training, IJCNN 2 (1990) 749-752.
3. C.M. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
4. D. Charles, Constrained PCA techniques for the identification of common factors in data, Neurocomputing 22 (1998) 145-156.
5. D. Charles, C. Fyfe, Modelling multiple cause structure using rectification constraints, Network: Comput. Neural Systems 9 (1998) 167-182.
6. D. Charles, Unsupervised neural networks for the identification of multiple causes in data, Ph.D. Thesis, University of Paisley, 1999.
7. S.S. Chen, Basis pursuit, Ph.D. Thesis, Stanford University, 1995.
8. P. Dayan, R. Zemel, Competition and multiple cause models, Neural Comput. 7 (1995) 565-579.
9. D. Field, What is the goal of sensory coding?, Neural Comput. 6 (1994) 555:601.
10. P. Földiák, M. Young, The Handbook of Brain Theory and Neural Networks, Sparse Coding in the Primate Cortex, MIT Press, Cambridge, MA, 1995, pp. 895-898.
11. P. Földiák, Models of sensory coding, Ph.D. Thesis, University of Cambridge, 1992.
12. C. Fyfe, B. Gabrys, ε-insensitive Hebbian learning, Proceedings of International Conference on Neural Networks and Artificial Intelligence ICNNAI'99, Brest, ISBN 985-6584-05-1, October 1999, pp. 10-18.
13. G. Harpur, R. Pragur, Development of entropy coding in a recurrent network, Network 7 (2) (1996) 277-284.
14. G. Hinton, Z. Ghahramani, Generative models for discovering sparse distributed representations, Philos. Trans. Roy. Soc. Ser. B 352 (1997) 1177-1190.
15. Z. Ghahramani, G. Hinton, Hierarchical non-linear factor analysis and topographical maps, in: M.I. Jordan, M.J. Kearns, S.A. Solla (Eds.), MIT Press, Cambridge, MA, 1998. Adv. Neural Inform. Process. Systems 10.
16. S. Hochreiter, J. Schmidhuber, Feature extraction through LOCOCODE, Neural Computation 11 (3) (1999) 679-714.
17. D.H. Hubel, T.N. Wiesel, Receptive fields, binocular interaction and functional architecture in the cats visual cortex, J. Physiol. (London) 160 (1962) 106-154.
18. J. Karhunen, J. Joutsensalo, Representation and separation of signals using non-linear PCA type learning, Neural Networks 7 (1994) 113-127.
19. M.S. Lewicki, T.J. Sejnowski, Bayesian unsupervised learning of higher order structure, Adv. Neural Inform. Process, Systems 9 (1996) 529-535.
20. E. Oja, Neural networks, principal components and subspaces, Int. J. Neural Systems 1 (1989) 61-68.
21. B. Olshausen, D. Field, Emergence of simple-cell receptive-field properties by learning a sparse code for natural images, Nature 381 (6583) (1996) 607-609.
22. E.T. Rolls, A. Treves, The relative advantages of sparse versus distributed encoding for neuronal networks in the brain, Network 1 (1990) 407-442.
23. D.E. Rumelhart, D. Zipser, Feature discovery by competitive learning, Cognitive Sci. 9 (1) (1985) 75-112.
24. T.D. Sanger, Analysis of the two-dimensional receptive fields learned by the generalized hebbian algorithm in response to random input, Biol. Cybernet. 63 (1990) 221-228.
25. E. Saund, A multiple-cause mixture model for unsupervised learning, Neural Comput. 7 (1995) 51-71.
26. L. Xu, Least mean square error reconstruction for self-organising neural-nets, Neural Networks 6 (1993) 627-648.
27. R.S. Zemel, A minimum description length framework for unsupervised learning, Ph.D. Thesis, Computer Science, University of Toronto, Canada, 1993.