Neural Computations by Asymmetric Networks with Nonlinearities

  • Naohiro Ishii
  • Toshinori Deguchi
  • Masashi Kawaguchi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4432)


Nonlinearity is an important factor in the biological visual neural networks. Among prominent features of the visual networks, movement detections are carried out in the visual cortex. The visual cortex for the movement detection, consist of two layered networks, called the primary visual cortex (V1),followed by the middle temporal area (MT), in which nonlinear functions will play important roles in the visual systems. These networks will be decomposed to asymmetric sub-networks with nonlinearities. In this paper, the fundamental characteristics in asymmetric neural networks with nonlinearities, are discussed for the detection of the changing stimulus or the movement detection in these neural networks. By the optimization of the asymmetric networks, movement detection equations are derived. Then, it was clarified that the even-odd nonlinearity combined asymmetric networks, has the ability in the stimulus change detection and the direction of movement or stimulus, while symmetric networks need the time memory to have the same ability. These facts are applied to two layered networks, V1 and MT.


Visual Cortex Movement Detection Amacrine Cell Impulse Response Function Stimulus Movement 
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.
    Hassenstein, B., Reichard, W.: Systemtheoretische analyse der zeit-, reihenfolgen- and vorzeichenauswertung bei der bewegungsperzeption des russelkafers. Chlorophanus. Z. Naturf. 11b, 513–524 (1956)Google Scholar
  2. 2.
    Barlow, H.B., Levick, R.W.: The mechanism of directional selectivity in the rabbit’s retina. J. Physiol. 173, 377–407 (1965)Google Scholar
  3. 3.
    Victor, J.D., Shapley, K.M.: The nonlinear pathway of Y ganglion cells in the cat retina. J. Gen. Physiol. 74, 671–689 (1979)CrossRefGoogle Scholar
  4. 4.
    Ishii, N., Naka, K.-I.: Movement and Memory Function in Biological Neural Networks. Int. J. of Artificial Intelligence Tools 4(4), 489–500 (1995)CrossRefGoogle Scholar
  5. 5.
    Ishii, N., Sugiura, S., Nakamura, M., Yamauchi, K.: Sensory Perception, Learning and Integration in Neural Networks. In: Proc. IEEE Int. Conf. on Information Intelligence & Systems, pp. 72–79 (1999)Google Scholar
  6. 6.
    Ishii, N., Naka, K.-I.: Function of Biological Asymmetrical Neural Networks. In: Cabestany, J., Mira, J., Moreno-Díaz, R. (eds.) IWANN 1997. LNCS, vol. 1240, pp. 1115–1125. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  7. 7.
    Korenberg, M.J., Sakai, H.M., Naka, K.-I.: Dissection of theneuronnetwork in the catfish inner retina. J. Neurophysiol. 61, 1110–1120 (1989)Google Scholar
  8. 8.
    Marmarelis, P.Z., Marmarelis, V.Z.: Analysis of Physiological System: The White Noise Approach. Plenum Press, New York (1978)Google Scholar
  9. 9.
    Naka, K.-I., Sakai, H.M., Ishii, N.: Generation of transformation of second order nonlinearity in catfish retina. Annals of Biomedical Engineering 16, 53–64 (1988)CrossRefGoogle Scholar
  10. 10.
    Shapley, R.: Visual cortex: pushing the envelope. Nature: neuroscience 1, 95–96 (1998)CrossRefGoogle Scholar
  11. 11.
    Reichardt, W.: Autocorrelation, a principle for the evaluation of sensory information by the central nervous system (Rosenblith Edition). Wiley, Chichester (1961)Google Scholar
  12. 12.
    Sakuranaga, M., Naka, K.-I.: Signal transmission in the catfish retina. III. Transmission to type-C cell. J. Neurophysiol. 58, 411–428 (1987)Google Scholar
  13. 13.
    Taub, E., Victor, J.D., Conte, M.M.: Nonlinear preprocessing in short-range motion. Vision Research 37, 1459–1477 (1997)CrossRefGoogle Scholar
  14. 14.
    Heeger, D.J.: Modeling simple-cell direction selectivity with normalized, half-squared, linear operators. J. Neurophysiol. 70, 1885–1898 (1993)Google Scholar
  15. 15.
    Heeger, D.J., Simoncelli, E.P., Movshon, J.A.: Computational models of cortical visual processing. Proc. Natl. Acad. Sci, USA 93, 623–627 (1996)CrossRefGoogle Scholar
  16. 16.
    Simoncelli, E.P., Heeger, D.J.: A Model of Neuronal Responses in Visual Area MT. Vision Research 38, 743–761 (1998)CrossRefGoogle Scholar
  17. 17.
    Lu, Z.L., Sperling, G.: Three-systems theory of human visual motion perception: review and update. J. Opt. Soc. Am. A 18, 2331–2370 (2001)CrossRefGoogle Scholar
  18. 18.
    Ishii, N., Deguchi, T., Sasaki, H.: Parallel Processing for Movement Detection in Neural Networks with Nonlinear Functions. In: Yang, Z.R., Yin, H., Everson, R.M. (eds.) IDEAL 2004. LNCS, vol. 3177, pp. 626–633. Springer, Heidelberg (2004)Google Scholar
  19. 19.
    Lee, Y.W., Schetzen, M.: Measurement of the Wiener kernels of a nonlinear system by cross-correlation. Int. J. Control 2, 237–254 (1965)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Naohiro Ishii
    • 1
  • Toshinori Deguchi
    • 2
  • Masashi Kawaguchi
    • 3
  1. 1.Aichi Institute of Technology, Yakusacho, Toyota 470–0392Japan
  2. 2.Gifu National College of Technology, Motosu, Gifu 501-0495Japan
  3. 3.Suzuka National College of Technology, Suzuka, Mie 510-0294Japan

Personalised recommendations