Motion Detection in Asymmetric Neural Networks

详细信息    查看全文

• 关键词：Asymmetrical neural networks ; Directional movement ; Nonlinear visual pathway ; Wiener kernels ; Motion detection
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9719
• 期：1
• 页码：409-417
• 全文大小：305 KB
• 参考文献：1.Reichard, W.: Autocorrelation, a principle for the evaluation of sensory information by the central nervous system. Rosenblith edn. Wiley, New York (1961)
  2.Adelson, E.H., Bergen, J.R.: Spatiotemporal energy models for the perception of motion. J. Opt. Soc. Am. A 2(2), 284–298 (1985)CrossRef
  3.Heess, N., Bai, R.W.: Direction opponency, not quadrature, is key to the 1/4 cycle preference for apparent motion in the motion energy model. J. Neurosci. 30(34), 11300–11304 (2010)CrossRef
  4.Chubb, C., Sperling, G.: Drift-Balanced Random Stimuli, A General Basis for Studying Non-Fourier Motion. J. Optical Soc. of America A, 1986–2006 (1988)
  5.Taub, E., Victor, J.D., Conte, M.: Nonlinear preprocessing in short-range motion. Vis. Res. 37, 1459–1477 (1997)CrossRef
  6.Simonceli, E.P., Heeger, D.J.: A model of neuronal responses in visual area MT. Vis. Res. 38, 743–761 (1996)CrossRef
  7.Heeger, D.J.: Normalization of cell responses in cat striate cortex. Vis. Neurosci. 9, 181–197 (1992)CrossRef
  8.Marmarelis, P.Z., Marmarelis, V.Z.: Analysis of Physiological Systems – The White Noise Approach. Plenum Press, New York (1978)CrossRef MATH
  9.Marmarelis, V.Z.: Nonlinear Dynamic Modeling of Physiological Systems. Wiley-IEEE Press, New Jersey (2004)CrossRef
  10.Marmarelis, V.Z.: Modeling methodology for nonlinear physiological systems. Ann. Biomed. Eng. 25, 239–251 (1997)CrossRef
  11.Wiener, N.: Nonlinear Problems in Random Theory. The MIT Press, Cambridge (1966)
  12.Sakuranaga, M., Naka, K.I.: Signal transmission in the catfish retina. III. Transmissioto type-C cell. J. Neurophysiol. 53(2), 411–428 (1985)
  13.Naka, K.I., Sakai, H.M., Ishii, N.: Generation of transformation of second order nonlinearity in catfish retina. Ann. Biomed. Eng. 16, 53–64 (1988)CrossRef
  14.Lee, Y.W., Schetzen, M.: Measurements of the Wiener kernels of a nonlinear by cross-correlation. Int. J. of Control 2, 237–254 (1965)CrossRef
  15.Ishii, N., Ozaki, M., Sasaki, H.: Correlation computations for movement detection in neural networks. In: Negoita, M.G., Howlett, R.J., Jain, L.C. (eds.) KES 2004. LNCS (LNAI), vol. 3214, pp. 124–130. Springer, Heidelberg (2004)CrossRef
  16.Ishii, N., Deguchi, T., Kawaguchi, M.: Neural computations by asymmetric networks with nonlinearities. In: Beliczynski, B., Dzielinski, A., Iwanowski, M., Ribeiro, B. (eds.) ICANNGA 2007. LNCS, vol. 4432, pp. 37–45. Springer, Heidelberg (2007)CrossRef
  
• 作者单位：Naohiro Ishii (16)
  Toshinori Deguchi (17)
  Masashi Kawaguchi (18)
  Hiroshi Sasaki (19)
  
  16. Aichi Institute of Technology, Toyota, Japan
  17. Gifu National College of Technology, Gifu, Japan
  18. Suzuka College of Technology, Mie, Japan
  19. Fukui University of Technology, Fukui, Japan
  
• 丛书名：Advances in Neural Networks ¨C ISNN 2016
• ISBN：978-3-319-40663-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9719

文摘

To make clear the mechanism of the visual movement is important in the visual system. The prominent feature is the nonlinear characteristics as the squaring and rectification functions, which are observed in the retinal and visual cortex networks. Conventional model for motion processing in cortex, is the use of symmetric quadrature functions with Gabor filters. This paper proposes a new motion sensing processing model in the asymmetric networks. To make clear the behavior of the asymmetric nonlinear network, white noise analysis and Wiener kernels are applied. It is shown that the biological asymmetric network with nonlinearities is effective and general for generating the directional movement from the network computations. The qualitative analysis is performed between the asymmetrical network and the conventional quadrature model. The results are applicable to the V1 and MT model of the neural networks in the cortex.