Journal of Medical Systems

, Volume 13, Issue 5, pp 243–252 | Cite as

A parallel implementation of the ALOPEX process

  • L. Melissaratos
  • E. Micheli-Tzanakou


Optimization techniques have found many applications in science, engineering, and industry. In all applications, the best value of a “cost function” is sought in a well-defined domain; this cost function in general depends on many parameters. An iterative optimization technique has been developed (ALOPEX) that uses feedback in order to optimize the response of a system. The cost function for this process is problem dependent and therefore quite flexible. The method has been applied successfully to different optimization problems such as pattern recognition, receptive field studies in the visual system of animals, curve fitting, etc. We present two special purpose hardware implementations for ALOPEX. The first method takes time O(logN + logm) and uses O(mN2) processing elements. The second method takes O(logN + m) time and uses O(N2) processing elements. Our basic architecture is a binary tree with N2 leaves (equal to the length of the vectors) and therefore had depth O(logN). Different implications of the two approaches will be discussed including similarities with the biological visual process.


Pattern Recognition Cost Function Field Study Visual System Optimization Technique 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kirkpatrick, S., Gelatt, C.D., Jr., and Vecchi, M.P., Optimization by simulated annealing.Science 220, 671–680, 1983.Google Scholar
  2. 2.
    Metropolis, N., Rosenbluth, A.W., Rosenbluth, M.N., Teller, A.H., and Teller, E., Equation of state calculations by fast computing machines.J. Chem. Phys. 21, 1087–1092, 1953.Google Scholar
  3. 3.
    Van der Meer, S., Stochastic cooling and the accumulation of antiprotons.Science 230, 900–906, 1985.Google Scholar
  4. 4.
    Hopfield, T.J., and Tank, D.W., Neural computation of decisions in optimization problems.Biol. Cybern. 52, 141–152, 1985.Google Scholar
  5. 5.
    Hinton, G.E., and Sejnowski, T.J., Optimal perceptual inference.Proc. IEEE CVPR 448–453, 1983.Google Scholar
  6. 6.
    Tzanakou, E., and Harth, E., Determination of visual receptive fields by stochastic methods.Biophysical J. 15, 421, 1973.Google Scholar
  7. 7.
    Harth, E., and Tzanakou, E., A stochastic method for determining visual receptive fields.Vision Res. 14, 1475–1482, 1974.Google Scholar
  8. 8.
    Tzanakou, E., Michalak, R., and Harth, E., The ALOPEX process: Visual receptive fields with response feedback.Biol. Cybern. 35, 161–174, 1979.Google Scholar
  9. 9.
    Micheli-Tzanakou, E., Nonlinear characteristics in the Frog's visual system.Biol. Cybern. 51, 53–63, 1984.Google Scholar
  10. 10.
    Deutsch, S., and Micheli-Tzanakou, E.,Neuroelectric Systems NYU Press, New York, 1987.Google Scholar
  11. 11.
    Harth, E., and Pandya, A.S., Dynamics of the ALOPEX process: Applications to optimization problems. InBiomathematics, and Related Computational Problems (L. Ricciardi, ed.), Kluwar Acad. Publ., pp. 459–471, 1988.Google Scholar
  12. 12.
    Micheli-Tzanakou, E., and O'Malley, K.G., Harmonic content of patterns and their correlations to VEP waveforms. IEEE 17th Annual Conf. of EMBS, pp. 426–430, 1985.Google Scholar
  13. 13.
    Harth, E., Pandya, A.S. and Unnikrishnan, K.P., Perception as an optimization process InProceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition IEEE Computer Society Press, Washington, D.C., 1986, pp. 662–665.Google Scholar
  14. 14.
    Harth, E., Pandya, A.S., and Unnikrishnan, K.P., Optimization of cortical responses by Feedback modification of sensory afferents—A model of Perception and REM sleep. To be published.Google Scholar
  15. 15.
    Harth, E., Kalogeropoulos, T., and Pandya, A.S., ALOPEX: A Universal stochastic optimization procedure. IEEE Proc. of Spec. Symp. on Maturing Technologies and Emerging Horizons in BME, 97–107, 1988.Google Scholar
  16. 16.
    Dasey, T.J., and Micheli-Tzanakou, E., A pattern recognition application of the ALOPEX process with hexagonal arrays. Int. Joint Conference on Neural Networks, Vol. II, 119–125, 1989.Google Scholar
  17. 17.
    Quinn, M.J.,Design of Efficient Algorithms for Parallel Computers McGraw Hill, New York, 1987.Google Scholar

Copyright information

© Plenum Publishing Corporation 1989

Authors and Affiliations

  • L. Melissaratos
    • 1
  • E. Micheli-Tzanakou
    • 1
  1. 1.From the Department of Biomedical Engineering, RutgersThe State University of New JerseyPiscataway

Personalised recommendations