Concerning the differentiability of the energy function in vector quantization algorithms

Neural Networks

Volumn 20, Issue 5, 2007, Pages 621-630

  Lepetz, Dominique ^a   Némoz Gaillard, Max ^a   Aupetit, Michaël ^b  

^a ECOLE DES MINES D ALÈS   (France)

^b CEA DAM DIF   (France)

Author keywords

Energy function; K means; Neural gas; Potential function; Pseudo potential; Self organizing maps; Vector quantization

Indexed keywords

ENERGY FUNCTIONS; K-MEANS; NEURAL GAS; POTENTIAL FUNCTIONS; PSEUDO POTENTIAL; SELF-ORGANIZING MAPS;

CONVERGENCE OF NUMERICAL METHODS; NEURAL NETWORKS; TOPOLOGY; VECTOR QUANTIZATION;

ALGORITHMS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; ENERGY; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; MEASUREMENT; PRIORITY JOURNAL;

ALGORITHMS; HUMANS; LEARNING; NEURAL NETWORKS (COMPUTER); NONLINEAR DYNAMICS; SIGNAL PROCESSING, COMPUTER-ASSISTED; STOCHASTIC PROCESSES;

EID: 34447638892     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2006.11.006     Document Type: Article

References (30)

1. Ahalt A., Krishnamurthy A.K., Chen P., and Melton D.E. Competitive learning algorithms for vector quantization. Neural Networks 3 (1990) 277-290
2. Albert A.E., and Gardner L.A. Stochastic approximation and nonlinear regression (1967), MIT Press, Cambridge, MA
3. Aupetit, M. 2000. A recruiting neural-gas for function approximation. In Proc. of IEEE int. joint conf. on neural networks
4. Aupetit M., Couturier P., and Massotte P. γ-observable neighbours for vector quantization. Self-organizing maps. Neural Networks 15 (2002) 1017-1027 [Special issue]
5. Benaïm M., Fort J.C., and Pagès G. Convergence of the one-dimensional Kohonen algorithm. Advances in Applied Probability 30 (1998) 850-869
6. Bottou, L. (1991). Stochastic gradient learning in neural networks. In Proceedings of neuro Nimes 91
7. Cottrell, M., Fort, J.C., & Pagès, G. (1994). Two or three things that we know about the kohonen algorithm. In Proc. of European symposium on artificial neural networks (pp. 271-276)
8. Cottrell M., Fort J.C., and Pagès G. Theoretical aspects of the som algorithm. Neurocomputing 21 (1998) 119-138
9. Erwin E., Obermayer K., and Schulten K. Self-organizing maps: Ordering, convergence properties and energy functions. Biological Cybernetics 67 (1992) 47-55
10. Fritzke B. Growing cell structures - a self-organizing network for unsupervised and supervised learning. Neural Networks 7 9 (1994) 1441-1460
11. Fritzke B. Growing grid - a self-organizing network with constant neighborhood range and adaptation strength. Neural Processing Letters 2 5 (1995) 9-13
12. Fritzke B. A growing neural-gas network learns topologies. In: Tesauro G., Touretzky D.S., and Leen T.K. (Eds). Advances in neural information processing systems (1995) 7
13. Göppert J., and Rosenstiel W. Varying cooperation in some for improved function approximation. Proc. of IEEE int. conf. on neural networks Vol. 1 (2000) 1-6
14. Gray R.M., and Neuhoff D.L. Quantization. IEEE Transactions on Information Theory 44 (1998) 2325-2384
15. Heskes T. Energy functions for self-organizing maps. In: Oja E., and Kaski S. (Eds). Kohonen maps (1999) 303-315
16. Heskes T., and Kappen B. Error potentials for self-organization. Proc. of IEEE int. conf. on neural networks Vol. 3 (1993) 1219-1223
17. Kangas J., Kohonen T., and Laaksonen J. Variants of self-organizing maps. IEEE Transactions on Neural Networks 1 1 (1990) 93-99
18. Kohonen T. Self-organized formation of topologically correct feature maps. Biological Cybernetics 43 (1982) 59-69
19. Kohonen T. Self-organization and associative memory formation (1988), Springer-Verlag
20. Kohonen T. Self-organizing maps: optimization approaches. Artificial neural networks Vol. 2 (1991), Elsevier Science Publishers 981-990
21. Linde Y., Buzzo A., and Gray R.M. An algorithm for vector quantizer design. IEEE Transactions on Communications 28 (1980) 84-95
22. Mac-Queen, J. (1967). Some methods for classification and analysis of multivariate observations. In Proc. of the fifth Berkeley symposium on mathematical statistics and probability. Vol. 1 (pp. 281-297) Berkeley: University of California Press
23. Martinetz T.M., Berkovitch S.G., and Schulten K.J. Neural-gas network for vector quantization and its application to time-series prediction. IEEE Transactions on Neural Networks 4 4 (1993) 558-569
24. Martinetz T.M., and Schulten K.J. Topology representing networks. Neural Networks 7 (1994) 507-522
25. Mou K.L., and Yeung D.Y. Gabriel networks: Self-organizing neural networks for adaptive vector quantization. Proc. of the int. symp. on speech, image processing and neural networks Vol. 2 (1994) 658-661
26. Okabe A., Boots B., and Sugihara K. Spatial tessellations: concepts and applications of Voronoïdiagrams (1992), John Wiley, Chichester
27. Pagès, G. (1993). Voronoï tesselation, space quantization algorithms and numerical integration. In Proc. of European symposium on artificial neural networks (pp. 221-228)
28. Robbins H., and Monro S. A stochastic approximation method. Annals of Mathematical Statistics 22 (1951) 400-407
29. Tolat V.V. An analysis of Kohonen's self-organizing maps using a system of energy functions. Biological Cybernetics 64 (1990) 155-164
30. Villmann, T., & Bauer, H.U. (1997). The gsom-algorithm for growing hypercubical output spaces in self-organizing maps. In Proc. of the workshop on self-organizing maps