What Is the Optimal Architecture for Visual Information Routing?

Analyzing the design of networks for visual information routing is an underconstrained problem due to insufficient anatomical and physiological data. We propose here optimality criteria for the design of routing networks. For a very general architecture, we derive the number of routing layers and the fanout that minimize the required neural circuitry. The optimal fanout l is independent of network size, while the number k of layers scales logarithmically (with a prefactor below 1), with the number n of visual resolution units to be routed independently. The results are found to agree with data of the primate visual system.

[1]  W. Pitts,et al.  How we know universals; the perception of auditory and visual forms. , 1947, The Bulletin of mathematical biophysics.

[2]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[3]  C. B. Shelman,et al.  Morphology of the primate optic nerve. 3. Fiber characteristics of the foveal outflow. , 1972, Investigative ophthalmology.

[4]  C. B. Shelman,et al.  Morphology of the primate optic nerve. I. Method and total fiber count. , 1972, Investigative ophthalmology.

[5]  H. Wässle,et al.  The cat optic nerve: Fibre total count and diameter spectrum , 2004, The Journal of comparative neurology.

[6]  Y. Fukuda,et al.  Strain differences in quantitative analysis of the rat optic nerve , 1982, Experimental Neurology.

[7]  R. Desimone,et al.  Selective attention gates visual processing in the extrastriate cortex. , 1985, Science.

[8]  H. Kennedy,et al.  Topography of the afferent connectivity of area 17 in the macaque monkey: A double‐labelling study , 1986, The Journal of comparative neurology.

[9]  Bruno A. Olshausen,et al.  Pattern recognition, attention, and information bottlenecks in the primate visual system , 1991, Defense, Security, and Sensing.

[10]  Joachim M. Buhmann,et al.  Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[11]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[12]  David I. Perrett,et al.  Modeling visual recognition from neurobiological constraints , 1994, Neural Networks.

[13]  D. V. van Essen,et al.  Responses in area V4 depend on the spatial relationship between stimulus and attention. , 1996, Journal of neurophysiology.

[14]  David J. Field,et al.  Sparse coding with an overcomplete basis set: A strategy employed by V1? , 1997, Vision Research.

[15]  Eric O. Postma,et al.  SCAN: A Scalable Model of Attentional Selection , 1997, Neural Networks.

[16]  Klaus Obermayer,et al.  Singularities in Primate Orientation Maps , 1997, Neural Computation.

[17]  M. Fahle,et al.  Limited translation invariance of human visual pattern recognition , 1998, Perception & psychophysics.

[18]  B. Fischer,et al.  Visual field representations and locations of visual areas V1/2/3 in human visual cortex. , 2003, Journal of vision.

[19]  Jörg Lücke,et al.  Rapid Processing and Unsupervised Learning in a Model of the Cortical Macrocolumn , 2004, Neural Computation.

[20]  G. Rager,et al.  Generation and degeneration of retinal ganglion cells in the chicken , 1976, Experimental Brain Research.

[21]  Christoph von der Malsburg,et al.  Maplets for correspondence-based object recognition , 2004, Neural Networks.

[22]  Rolf P. Würtz,et al.  Image Representation by Complex Cell Responses , 2004, Neural Computation.

[23]  David D. Cox,et al.  'Breaking' position-invariant object recognition , 2005, Nature Neuroscience.

[24]  E. L. Schwartz,et al.  Spatial mapping in the primate sensory projection: Analytic structure and relevance to perception , 1977, Biological Cybernetics.

[25]  Jörg Lücke,et al.  Dynamics of Cortical Columns - Sensitive Decision Making , 2005, ICANN.

[26]  I. Fujita,et al.  Organization of horizontal axons in the inferior temporal cortex and primary visual cortex of the macaque monkey. , 2005, Cerebral cortex.

[27]  D. Kersten,et al.  The representation of perceived angular size in human primary visual cortex , 2006, Nature Neuroscience.

[28]  Jörg Lücke,et al.  Rapid Convergence to Feature Layer Correspondences , 2008, Neural Computation.