Wire length as a circuit complexity measure

We introduce wire length as a salient complexity measure for analyzing the circuit complexity of sensory processing in biological neural systems. This new complexity measure is applied in this paper to two basic computational problems that arise in translation- and scale-invariant pattern recognition, and hence appear to be useful as benchmark problems for sensory processing. We present new circuit design strategies for these benchmark problems that can be implemented within realistic complexity bounds, in particular with linear or almost linear wire length. Finally, we derive some general bounds which provide information about the relationship between new complexity measure wire length and traditional circuit complexity measures.

[1]  Pietro Perona,et al.  Unsupervised Learning of Models for Recognition , 2000, ECCV.

[2]  Chun Zhang,et al.  Storing and querying ordered XML using a relational database system , 2002, SIGMOD '02.

[3]  John Lazzaro,et al.  Winner-Take-All Networks of O(N) Complexity , 1988, NIPS.

[4]  Christof Koch,et al.  Biophysics of Computation: Information Processing in Single Neurons (Computational Neuroscience Series) , 1998 .

[5]  John E. Savage,et al.  Models of computation - exploring the power of computing , 1998 .

[7]  G. Mitchison.  Axonal trees and cortical architecture , 1992, Trends in Neurosciences.

[8]  D. Chklovskii.  Binocular disparity can explain the orientation of ocular dominance stripes in primate primary visual area (V1) , 2000, Vision Research.

[9]  W. Precht.  The synaptic organization of the brain G.M. Shepherd, Oxford University Press (1975). 364 pp., £3.80 (paperback) , 1976, Neuroscience.

[10]  Prof. Dr. Dr. Valentino Braitenberg,et al.  Cortex: Statistics and Geometry of Neuronal Connectivity , 1998, Springer Berlin Heidelberg.

[11]  D. Chklovskii,et al.  A wire length minimization approach to ocular dominance patterns in mammalian visual cortex , 2000 .

[12]  Robert A. Legenstein,et al.  Neural circuits for pattern recognition with small total wire length , 2002, Theor. Comput. Sci..

[13]  Moshe Abeles,et al.  Corticonics: Neural Circuits of Cerebral Cortex , 1991 .

[14]  R. Guillery.  Histology of the Nervous System by Santiago Ramón y Cajal. Translated into English from the French edition by Neely Swanson and Larry W. Swanson, Oxford University Press, 1995. $195.00 (1672 pp) ISBN 0 19 507 4017 , 1996, Trends in Neurosciences.

[15]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[16]  M. Rem,et al.  Cost and performance of VLSI computing structures , 1979, IEEE Transactions on Electron Devices.

[17]  L. Garey.  Cortex: Statistics and Geometry of Neuronal Connectivity, 2nd edn. By V. BRAITENBERG and A. SCHÜZ. (Pp. xiii+249; 90 figures; ISBN 3 540 63816 4). Berlin: Springer. 1998. , 1999 .

[18]  Nimrod Megiddo,et al.  Range queries in OLAP data cubes , 1997, SIGMOD '97.

[19]  Dmitri B. Chklovskii,et al.  Wiring Optimization in the Brain , 1999, NIPS.

[20]  W. R. Adey.  The synaptic organization of the brain. 2nd edn. , 1981 .

[21]  Carver Mead,et al.  Analog VLSI and neural systems , 1989 .

[22]  Charles E. Leiserson,et al.  Fat-trees: Universal networks for hardware-efficient supercomputing , 1985, IEEE Transactions on Computers.

[23]  Pietro Perona,et al.  A Bayesian approach to unsupervised one-shot learning of object categories , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.