Abstract
We describe an implementation of a vector quantization codebook design algorithm based on the frequencysensitive competitive learning artificial neural network. The implementation, designed for use on high-performance computers, employs both multitasking and vectorization techniques. A C version of the algorithm tested on a CRAY Y-MP8/864 is discussed. We show how the implementation can be used to perform vector quantization, and demonstrate its use in compressing digital video image data. Two images are used, with various size codebooks, to test the performance of the implementation. The results show that the supercomputer techniques employed have significantly decreased the total execution time without affecting vector quantization performance.
Similar content being viewed by others
References
Ahalt, S.C., Krishnamurthy, A.K., Chen, P., and Melton, D.E. 1990. Competitive learning algorithms for vector quantization. Neural Networks, 3: 277–290.
Buzo, A., Gray, Jr., A.H., Gray, R.M., and Markel, J.D. 1980. Speech coding based upon vector quantization. IEEE Trans. Acoustics, Speech, and Signal Processing, ASSP-28, 5: 562–574.
Chen, P. 1989. The neural shell: A neural networks simulation tool, and an application. Master's thesis, The Ohio State Univ., Columbus, Oh.
Cray Research, Inc. 1989. Cray C Reference Manual SR-2024 D. Mendota Heights, Minn.
DeSieno, D. 1988. Adding a conscience to competitive learning. In IEEE 2nd Internat. Neural Network Conf. (San Diego), pp. 117–124.
Forrest, B.M., Roweth, D., Stroud, N., Wallace, D.J., and Wilson, G.V. 1987. Implementing neural network models on parallel computers. Computer, 30, 5: 413–419.
Gersho, A. 1982. On the structure of vector quantizers. IEEE Trans. Inf. Theory, 28, 2: 157–166.
Gray, R.M. 1984. Vector quantization. IEEE ASSP Magazine, 1, 2: 4–29.
Grossberg, S. 1976a. Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors. Biological Cybernetics, 23: 121–134.
Grossberg, S. 1976b. Adaptive pattern classification and universal recoding: II. Feedback, expectation, olfaction, illusions. Biological Cybernetics, 23: 187–202.
Grossberg, S. 1987. Competitive learning: From interactive activation to adaptive resonance. Cognitive Science, 11: 23–63.
Hecht-Nielsen, R. 1988. Applications of counterpropagation networks. Neural Networks, 1, 2:131–141.
Jain, A.K. 1981. Image data compression: A review. Proc. IEEE, 69, 3: 349–389.
Kohonen, T. 1984. Self-Organization and Associative Memory. Springer-Verlag, Berlin.
Kohonen, T. 1988a. An introduction to neural computing. Neural Networks, 1, 1: 3–16.
Kohonen, T. 1988b. Learning vector quantization. In Abstracts of the First Annual INNS Meeting (Boston), p. 303.
Kohonen, T. 1988c. Self-Organization and Associative Memory, 2nd ed. Springer-Verlag, Berlin.
Krishnamurthy, A., Ahalt, S., Melton, D., and Chen, P. 1990. Neural networks for vector quantization of speech and images. IEEE J. Selected Areas in Communications, 8, 8: 1449–1457.
Larson, J.L. 1984. Multitasking on the Cray X-MP-2 multiprocessor. Computer, 17, 7: 62–69.
Lee, T.C., and Peterson A.M. 1990. Adaptive vector quantization using a self-development neural network. IEEE J. Selected Areas in Communications, 8, 8: 1458–1471.
Linde, Y., Buzo, A., and Gray, R.M. 1980. An algorithm for vector quantizer design. IEEE Trans. Communications, COM-28, 1: 84–95.
Lloyd, S.P. 1982. Least-square quantization in PCM. IEEE Trans. Inf. Theory, 28, 2: 129–137.
Luttrell, S.P. 1990. Derivation of a class of training algorithms. IEEE Trans. Neural Networks, 1, 2: 229–232.
Makhoul, J., Roucos, S., and Gish, H. 1985. Vector quantization in speech coding. Proc. IEEE, 73, 11: 1551–1588.
Matsuyama, Y. 1988. Vector quantization with optimized grouping and parallel distributed processing. J. Neural Networks, 1 (supplement 1), 36.
Melton, D.E. 1988. Vector quantization of speech using neural networks. Master's thesis, The Ohio State Univ., Columbus, Oh.
Nasrabadi, N., and King, R.A. 1988. Image coding using vector quantization: A review. IEEE Trans. Communications, 36, 8: 957–971.
Nasrabadi, N.M., and Feng, Y. 1988. Vector quantization of images based on the Kohonen self-organizing feature maps. In IEEE Internat. Conf. on Neural Networks, vol. I, pp. 101–108.
Naylor, J., and Li, K.P. 1988. Analysis of a neural network algorithm for vector quantization of speech parameters. In Proc., First Annual INNS Meeting (Boston), p. 310.
Netravali, A.N., and Limb, J.O. 1980. Picture coding: A review. Proc. IEEE, 68, 3: 366–407.
Padua, D.A., and Wolfe, M.J. 1986. Advanced compiler optimizations for supercomputers. CACM, 29, 12: 1184–1201.
Rumelhart, D., and Zipser, D. 1985. Feature discovery by competitive learning. Cognitive Science, 9: 75–112.
Rumelhart, D.E., McClelland, J.L., and the PDP research group. 1986. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. I: Foundations. MIT Press, Cambridge, Mass.
Salisbury, K., Townsend, W., Eberman, B., and DiPietro, D. 1988. Preliminary design of a whole-arm manipulation system (WAMS). In Proc., 1988 IEEE Internat. Conf. on Robotics and Automation, Vol. I (Philadelphia), pp. 254–260.
Shannon, C.E. 1949. The Mathematical Theory of Communication. Univ. Ill. Press, Urbana, Ill.
Shannon, C.E. 1960. Coding theorem for a discrete source with a fidelity criterion. In Information and Decision Processes (R.E. Machol, ed.), McGraw-Hill, New York.
Van den Bout, D.E., and Miller III, T.K. 1989. TInMANN: The Integer Markovian Artificial Neural Network. In Proc., Internat. Joint Conf. on Neural Networks (Washington, D.C.), pp. II-205–II-211.
Zhou, Y.-T., Chellappa, R., Vaid, A., and Jenkins, B.K. 1988. Image restoration using a neural network. IEEE Trans. Acoustics, Speech, and Signal Processing, 36, 7: 1141–1151.
Author information
Authors and Affiliations
Additional information
This work was supported by a Cray University Research Award and by NASA Lewis research grant number NAG3-1164.
Rights and permissions
About this article
Cite this article
Ahalt, S.C., Chen, P., Chou, CT. et al. Implementation of a vector quantization codebook design technique based on a competitive learning artificial neural network. J Supercomput 5, 307–330 (1992). https://doi.org/10.1007/BF00127951
Issue Date:
DOI: https://doi.org/10.1007/BF00127951