Faithful representations with topographic maps

Neural Networks

Volumn 12, Issue 6, 1999, Pages 803-823

  Van Hulle, M M ^a  

^a UNIVERSITY OF LEUVEN   (Belgium)

Author keywords

Conscience learning; Equiprobabilistic maps; Faithful representations; Gabor functions; Non parametric density estimation; Topographic maps; Wavelet filters

Indexed keywords

ADAPTIVE FILTERING; ALGORITHMS; LEARNING SYSTEMS; PROBABILITY;

FAITHFUL REPRESENTATIONS; GABOR FUNCTION; MAXIMUM ENTROPY LEARNING RULES (KMER); TOPOGRAPHIC MAPS;

NEURAL NETWORKS;

ALGORITHM; DENSITY; ENTROPY; ERROR; LEARNING; MATHEMATICAL ANALYSIS; MODEL; NERVE CELL NETWORK; PRIORITY JOURNAL; PROBABILITY; REVIEW; TOPOGRAPHY;

EID: 0032773697     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00041-6     Document Type: Article

References (56)

1. Adelson E.H., Bergen J.R. Spatiotemporal energy models for the perception of motion. Journal of Optical Society of America A. 2:1985;284-299.
2. Ahalt S.C., Krishnamurthy A.K., Chen P., Melton D.E. Competitive learning algorithms for vector quantization. Neural Networks. 3:1990;277-290.
3. Bauer H.U., Der R., Herrmann M. Controlling the magnification factor of self-organizing feature maps. Neural Computation. 8:1996;757-771.
4. Bishop C. Neural networks for pattern recognition. 1995;Clarendon, Oxford.
5. Breiman L., Meisel W., Purcell E. Variable kernel estimates of multivariate densities. Technometrics. 19:1977;135-144.
6. Chinrungrueng C., Séquin C.H. Optimal adaptive k-means algorithm with dynamic adjustment of learning rate. IEEE Transactions on Neural Networks. 6:1995;157-169.
7. Dersch D.R., Tavan P. Asymptotic level density in topological feature maps. IEEE Transactions on Neural Networks. 6:1995;230-236.
8. DeSieno, D. (1988). Adding a conscience to competitive learning. Proceedings of the IEEE International Conference on Neural Networks (vol. I, pp. 117-124). San Diego.
9. Duda R.O., Hart P.E. Pattern classification and scene analysis. 1973;Wiley, New York.
10. Field D.J. What is the goal of sensory coding? Neural Computation. 6:1994;559-601.
11. Fritzke B. Fast learning with incremental RBF networks. Neural Processing Letters. 1:(1):1994;2-5.
12. Gabor D. Theory of communication. Journal of IEE. 93:1946;429-457.
13. Galanopoulos A.S., Ahalt S.C. Codeword distribution for frequency sensitive competitive learning with one-dimensional input data. IEEE Transactions on Neural Networks. 7:1996;752-756.
14. Gersho A. Asymptotically optimal block quantization. IEEE Transactions on Information Processing. IT-25:1979;373-380.
15. Graepel T., Burger M., Obermayer K. Phase transitions in stochastic self-organizing maps. Physical Review E. 56:(4):1997;3876-3890.
16. Grossberg S. Adaptive pattern classification and universal recoding: I Parallel development and coding of neural feature detectors. Biological Cybernetics. 23:1976;121-134.
17. Herbin M., Bonnet N., Vautrot P. A clustering method based on the estimation of the probability density function and on the skeleton by influence zones. Application to image processing. Pattern Recognition Letters. 17:1996;1141-1150.
18. Kim Y.K., Ra J.B. Adaptive learning method in self-organizing map for edge preserving vector quantization. IEEE Transactions on Neural Networks. 6:1995;278-280.
19. Kohonen, T., Raivo, K., Simula, O., Ventä, O., Henriksson, J., (1996). Combining linear equalization and self-organizing adaptation in dynamic discrete-signal detection. Proceedings of IJCNN (pp. I223-I228). San Diego, CA, 17-21 June.
20. Kohonen T., Kaski S., Lappalainen H. Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM. Neural Computation. 9:1997;1321-1344.
21. Kohonen T. Self-organized formation of topologically correct feature maps. Biological Cybernetics. 43:1982;59-69.
22. Kohonen T. Self-organization and associative memory. 1984;Springer, Berlin.
23. Kohonen T. Self-organizing maps. 1995;Springer, Berlin.
24. Lin J.K., Grier D.G., Cowan J.D. Faithful representation of separable distributions. Neural Computation. 9:1997;1305-1320.
25. Linsker R. How to generate ordered maps by maximizing the mutual information between input and output signals. Neural Computation. 1:1989;402-411.
26. Ljung L. Analysis of recursive stochastic algorithms. IEEE Transactions on Automatic Control. AC-22:1977;551-575.
27. Moody J., Darken C. Learning with localized receptive fields. Touretzky D., Hinton G., Sejnowski T. Proceedings of the 1988 Connectionist Models Summer School. 1988;133-143 Morgan Kaufmann, San Mateo.
28. Moreau E., Macchi O. High-order contrasts for self-adaptive source separation. Internationl Journal of Adaptive Control and Signal Processing. 10:1996;19-46.
29. Mulier F., Cherkassky V. Self-organization as an iterative kernel smoothing process. Neural Computation. 7:1995;1165-1177.
30. Nowlan S.J. Maximum likelihood competitive learning. Touretzky D.S. Advances in neural information processing systems II (Denver 1989). 1990;574-582 Morgan Kaufmann, San Mateo.
31. Olshausen B.A., Field D.J. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature. 381:1996;607-609.
32. Pagès G. Voronoi tessellation, space quantization algorithms and numerical integration. Verleysen M. Proceedings of the European Symposium on Artificial Neural Networks - ESANN'93, Brussels, Belgium. 1993;221-228.
33. Pajunen P., Hyvärinen A., Karhunen J. Nonlinear blind source separation by self-organizing maps. Amari S.-I., Chan L.-W., King I., Leung K.-S. Proceedings of the International Conference on Neural Information Processing (ICONIP'96). Progress in neural information processing. 2:1996;1207-1210 Springer, Berlin.
34. Poggio T., Girosi F. Regularization algorithms for learning that are equivalent to multilayer networks. Science. 247:1990;978-982.
35. Press W.H., Flannery B.P., Teukolsky S.A., Vetterling W.T. Numerical recipes. The art of scientific computing. 1990;Cambridge University Press, Cambridge.
36. Ritter H., Schulten K. On the stationary state of Kohonen's self-organizing sensory mapping. Biological Cybernetics. 54:1986;99-106.
37. Ritter H., Schulten K. Combining self-organizing maps. Proceedings of the International Joint Conference on Neural Networks. 2:1989;499-502.
38. Ritter H., Martinetz T., Schulten K. Neural computation and self-organizing maps: an introduction. 1992;Addison-Wesley, Reading, MA.
39. Ritter H. Asymptotic level density for a class of vector quantization processes. IEEE Transactions on Neural Networks. 2:(1):1991;173-175.
40. Rojas R. Neural networks. A systematic introduction. 1996;Springer, Berlin.
41. Rose K., Gurewitz E., Fox G.C. Statistical mechanics and phase transitions in clustering. Physical Review Letters. 65:(8):1990;945-948.
42. Shannon C.E. Coding theorem for a discrete source with a fidelity criterion. Machol R.E. Information and decision processes. 1960;McGraw-Hill, New York.
43. Silverman B.W. Density estimation for statistics and data analysis. 1992;Chapman and Hall, London.
44. Stone M. Cross-validation choice and assessment of statistical predictions. Journal of the Royal Statistical Society B. 36:1984;111-147.
45. TIMIT (1990). DARPA TIMIT acoustic-phonetic speech corpus. NIST Speech Disc 1-1.1 (CD-ROM).
46. Ueda, N., & Nakano, R. (1993). A new learning approach based on equidistortion principle for optimal vector quantizer design. Proceedings of the IEEE NNSP93 (pp. 362-371). Linthicum Heights, MD.
47. Van den Bout, D. E., & Miller III, T. K. (1989). TInMANN: the integer Markovian artificial neural network, Proceedings of the International Joint Conference on Neural Networks (II205-II211). Englewood Cliffs, NJ: Erlbaum.
48. Van Hulle M.M., Martinez D. On an unsupervised learning rule for scalar quantization following the maximum entropy principle. Neural Computation. 5:1993;939-953.
49. Van Hulle, M.M., (1995). Globally-ordered topology-preserving maps achieved with a learning rule performing local weight updates only. Proceedings of the IEEE NNSP95 (pp. 95-104). Cambridge, MA.
50. Van Hulle M.M. The formation of topographic maps that maximize the average mutual information of the output responses to noiseless input signals. Neural Computation. 9:(3):1997;595-606.
51. Van Hulle M.M. Nonparametric density estimation and regression achieved with topographic maps maximizing the information-theoretic entropy of their outputs. Biological Cybernetics. 77:1997;49-61.
52. Van Hulle M.M. Topology-preserving map formation achieved with a purely local unsupervised competitive learning rule. Neural Networks. 10:(3):1997;431-446.
53. Wässle H., Grünert U., Röhrenbeck J., Boycott B.B. Cortical magnification factor and the ganglion cell density of the primate retina. Nature. 341:1989;643-646.
54. Xu L., Jordan M.I. Unsupervised learning by EM algorithm based on finite mixture of Gaussians. World Congress on Neural Networks (Portland, OR). 2:1993;431-434.
55. Zadeh L.A. Fuzzy sets. Information and control. 8:1965;338-353.
56. Zador P.L. Asymptotic quantization error of continuous signals and the quantization dimension. IEEE Transactions on Information Theory. 28:1982;149-159.