Competitive Learning and Soft Competition for Vector Quantizer Design

IEEE Transactions on Signal Processing

Volumn 40, Issue 2, 1992, Pages 294-309

  Gersho, Allen ^c  

^a IBM HAIFA RESEARCH LAB   (Israel)

^b UNIVERSITY OF HAWAII   (United States)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING SYSTEMS; MATHEMATICAL TECHNIQUES - ALGORITHMS; MATHEMATICAL TECHNIQUES - CONVERGENCE OF NUMERICAL METHODS;

CONVERGENCE ANALYSIS; LEARNING ALGORITHMS; VECTOR QUANTIZERS; VOICE PROCESSING;

SPEECH;

EID: 0026821121     PISSN: 1053587X     EISSN: 19410476     Source Type: Journal    
DOI: 10.1109/78.124940     Document Type: Article

References (41)

1. A. Gersho, “On the structure of vector quantizers,” IEEE Trans. Inform. Theory, vol. IT-28, pp. 157–166, Mar. 1982.
2. R. M. Gray, “Vector quantization,” IEEE ASSP Mag., vol. 1. pp. 4–29, 1984.
3. Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Trans. Commun., vol. COM-28, pp. 84–95, Jan. 1980.
4. S. P. Lloyd, “Least-squares quantization in PCM,” IEEE Trans. Inform. Theory, vol. IT-28, pp. 129–137, Mar. 1982.
5. R. M. Gray and E. D. Kamin, “Multiple local optima in vector quantizers,” IEEE Trans. Inform. Theory, vol. IT-28, no. 2, pp. 256–261, Mar. 1982.
6. K. Zeger, J. Vaisey, and A. Gersho, “Globally optimal vector quantizer design by stochastic relaxation,” IEEE Trans. Signal Processing, this issue, pp. 310–322.
7. T. Kohonen, Self-Organization and Associative Memory. Berlin: Springer, 1984.
8. N. M. Nasrabadi and Y. Feng, “Vector quantization of images based upon the Kohonen self-organization feature maps,” in Proc. 2nc ICNNConf, vol. I, 1988, pp. 101–105.
9. B. Widrow and M. E. Hoff, “Adaptive switching circuits,” in 1960 IRE WESCON Conv. Rec., part 4, 1960, pp. 96–104.
10. B. Widrow and S. D. Stearns, Adaptive Signal Processing. Englewood Cliffs, NJ: Prentice-Hall, 1985.
11. P.C. Chang and R. M. Gray, “Gradient algorithms for designing predictive vector quantizers,” IEEE Trans. Acoust., Speech, Signal Processing, vol. ASSP-34, pp. 679–690, Aug. 1986.
12. A. Gersho, “Adaptive vector quantization,” Ann. Telecommun., vol. 41, no. 9–10, pp. 470–480, Sept.-Oct. 1986.
13. E. Eweda and O. Macchi, “Convergence of an adaptive linear esti mation algorithm,” IEEE Trans. Automat. Contr., vol. AC-29, pp. 119–127, Feb. 1984.
14. S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images,” IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-6, pp. 721–741, Nov. 1984.
15. K. Fukushima, “Cognitron: A self-organizing multilayer neural network,” Biol. Cybern., vol. 20, pp. 121–136, 175.
16. S. Grossberg, “Adaptive pattern classification and universal recoding, Part I: Parallel development and coding of neural feature detectors,” Biol. Cybern., vol. 23, pp. 121–134, 1976.
17. C. Von der Malsburg, “Self-organizing of orientation sensitive cells in the striate cortex,” Kibernetik, vol. 14, pp. 85–100, 1973.
18. D. E. Rumelhart and D. Zisper, “Feature discovery by competitive learning,” Cognitive Sci., vol. 9, pp. 75–112, 1985.
19. D. DeSieno, “Adding a conscience to competitive learning,” in Proc. 2nd I CNN Conf, vol. I, 1988, pp. 117–124.
20. H. Ritter and K. Schulten, “Kohonen's self-organization maps: Exploring their computational capabilities,” in Proc. 2nd ICNN Conf. vol. I, 1988, pp. 109–116.
21. H. L. Van Trees, Detection, Estimation, and Modulation Theory New York: Wiley, 1968.
22. T. Kohonen, “The ‘neural’ phonetic typewriter,” Computer, vol. 21. pp. 11-22,1988.
23. G. D. Tattersall, P. W. Linford, and R. Linggard, “Neural array for speech recognition,” Brit. Telecom. Technol. J., vol. 6, pp. 140-163, 1988.
24. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning in ternal representations by error propagation,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1. Cambridge, MA: M.I.T. Press/Bradford Books, 1986, ch. 8.
25. H. Bourlard and C. J. Wellekens, “Multilayer perceptrons and automatic speech recognition,” in Proc. 1st ICNN Conf, vol. 4, 1987, pp. 407–415.
26. H. Bourlard and C. J. Wellekens, “Speech dynamics and recurrent neural networks,” in Proc. IEEE ICASSP-89, 1989.
27. T. J. Sejnowski and C. R. Rosenberg, “NETtalk: A parallel that learns to read aloud,” Johns Hopkins Univ., Tech. Rep. JHU/ EECS-86/01, 1986.
28. A. Weibel, T. Hanazawa, G. Hinton, K. Shikano, and K. J. Lang, “Phoneme recognition using time-delay neural networks,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 37, pp. 328–339. 1989.
29. D. J. Burr, “Experiments on neural net recognition of spoken written text,” IEEE Trans. Acoust., Speech, Signal Processing, vol. 36, pp. 1162–1168, 1988.
30. L.Y. Cun, “HLM: A multilayer learning network,” in Proc. 1986 Connectionist Models Summer School (Camegie-Mellon Univ., Pittsburgh, PA), 1986, pp. 169–177.
31. R. P. Gorman and T. J. Sejnowski, “Analysis of hidden units in a layered network trained to classify sonar targets,” J. Neural networks, vol. 1, pp. 75–89, 1988.
32. A. H. Kramer and A. S. Vincentelli, “Efficient parallel learning algorithms for neural networks,” in Proc. NIPS Conf. 1988, D. Touretzky Ed., 1989, pp. 40–48.
33. S. Kullback, Information Theory and Statistics. New York, Wiley, 1959.
34. H. J. Sussmann, “On the convergence of a learning algorithm for Boltzmann machines,” Rutgers Univ., Tech. Rep. SYCON-88-03 1988.
35. S. Kirkpatrick, C. D. Gelatt, and M. P. Vecchi, “Optimization by simulated annealing,” Science, vol. 220, pp. 671–680, May 13, 1983.
36. N. Metropolis, A. W. Rosenbluth, M. N. Rosenbluth, A. H. Teller, and E. Teller, “Equations of state calculations by fast computing machines,” J. Chem. Phys., vol. 21, pp. 1087–1091, 1953.
37. P. J. M. Laarhoven and E. H. L. Aarts, Simulated Annealing: Theory and Applications. Dordrecht, Holland: D. Reidel, 1987.
38. G. E. Hinton, T. J. Sejnowski, and D. H. Ackley, “Boltzmann machines: Constraint satisfaction networks that learn,” Camegie-Melon Tech. Rep., 1984.
39. G. E. Hinton and T. J. Sejnowski, “Learning and relearning in Boltzmann machines,” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: M.I.T. Press/Bradford Books, 1986, ch. I.
40. E. Yair and A. Gersho, “The Boltzmann perception classifier,” J. Neural Networks, vol. 3, no. 2, pp. 203–221, Mar. 1990.
41. K. Zeger, “Corrections to ‘Gradient algorithms for designing predictive vector quantizers,”’ IEEE Trans. Signal Processing, vol. 39, no 3, pp. 764–765, Mar. 1991.