Connectionist techniques for the identification and suppression of interfering underlying factors

International Journal of Pattern Recognition and Artificial Intelligence

Volumn 17, Issue 8, 2003, Pages 1447-1466

  Corchado, Emilio ^a   Fyfe, Colin ^b  

^a UNIVERSITY OF BURGOS   (Spain)

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

Author keywords

insensitive Hebbian learning rule; Maximum minimum likelihood Hebbian learning; Negative feedback network; Rectified Gaussian distribution

Indexed keywords

DATA REDUCTION; LEARNING SYSTEMS; MAXIMUM LIKELIHOOD ESTIMATION; NEURAL NETWORKS;

Ε-INSENSITIVE HEBBIAN LEARNING RULE; MAXIMUM LIKELIHOOD HEBBIAN LEARNING; MINIMUM LIKELIHOOD HEBBIAN LEARNING; NEGATIVE FEEDBACK NETWORKS; RECTIFIED GAUSSIAN DISTRIBUTION;

PATTERN RECOGNITION;

EID: 0842267461     PISSN: 02180014     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0218001403002915     Document Type: Article

References (23)

1. H. B. Barlow and D. J. Tolhurst, "Why do you have edge detectors," 1992 Optical Society of America Annual Meeting, 1992 Technical Digest series, Vol. 23, Albuquerque, NM, Optical Society of America, Washington.
2. D. P. Bertsekas, Nonlinear Programming, Athena Scientific, Belmont, MA, 1995.
3. C. M. Bishop, Neural Networks for Pattern Recognition, Clarendon Press, Oxford, 1995.
4. D. Charles and C. Fyfe, "Modelling multiple cause structure using rectification constraints," Network: Comput. Neural Syst. 9 (1998) 167-182.
5. D. Charles, C. Fyfe, D. MacDonald and J. Koetsier, "Unsupervised neural networks for the identification of mimimum overcomplete basis in visual data," Neurocomputing 47 (2002) 119-143.
6. D. Charles, "Unsupervised artificial neural networks for the identification of multiple causes in data," Ph.D. Thesis, University of Paisley, 1999.
7. E. Corchado, D. Charles and C. Fyfe, "Rectified Gaussian distributions and the formation of local filters from video," 9th Eur. Symp. Artificial Neural Networks, ESANN'2001, April 2001, pp. 397-402.
8. D. J. Field, "What is the goal of sensory coding?" Neural Comput. 6 (1994) 559-601.
9. P. Földiek, "Models of sensory coding," Ph.D. Thesis, University of Cambridge, 1992.
10. C. Fyfe, "PCA properties of interneurons," From Neurobiology to Real World Computing, Proc. Int. Conf. Artificial Neural Networks, ICANN'93, 1993, pp. 183-188.
11. C. Fyfe, "A neural network for PCA and beyond," Neural Process. Lett. 6 (1997) 33-41.
12. C. Fyfe and D. Charles, Using Noise to Form a Minimal Overcomplete Basis, ICANN '99, 1999, pp. 708-713.
13. C. Fyfe and D. MacDonald, "ε-insensitive Hebbian learning," Neurocomputing 47 (2002) 35-57.
14. Z. Ghahramani and G. E. Hinton, "Hierarchical nonlinear factor analysis and topographical maps," Advances in Neural Information Processing Systems, NIPS10, cd version nips100486.djvu, 1998.
15. Y. Han and C. Fyfe, "An investigation of video data using neural networks for factor analysis and principal component analysis," Comput. Inform, Syst. J. 8 (2001) 9-76.
16. A. Hyvärinien, "Complexity pursuit: separating interesting components from time series," Neural Comput. 13 (2001) 883-898.
17. E. Oja, "Neural networks, principal components and subspaces," Int. J. Neural Syst. 1 (1989) 61-68.
18. E. Oja, H. Ogawa and J. Wangviwattana, "Principal components analysis by homogeneous neural networks, Part 1: The weighted subspace criterion," IEICE Trans. Inform. Syst. E75D (1992) 366-375.
19. E. Saund, "A multiple-cause mixture model for unsupervised learning," Neural Comput. 7 (1995) 51-71.
20. H. S. Seung, N. D. Socci and D. D. Lee, "The rectified Gaussian distribution," Ad. Neural Inform. Process. Syst. 10 (1998) 350-356.
21. A. J. Smola and B. Scholkopf, "A tutorial on support vector regression," Technical Report NC2-TR-1998-030, NeuroCOLT2 Technical Report Series, October 1998.
22. R. H. White, "Competitive Hebbian learning: algorithm and demonstration," Neural Networks 5 (1992) 261-275.
23. L. Xu, "Least mean square error reconstruction for self-organizing nets," Neural Networks 6 (1993) 627-648.