HOME HELP FEEDBACK SUBSCRIPTIONS ARCHIVE SEARCH TABLE OF CONTENTS		QUICK SEARCH:   [advanced] Author: Keyword(s): Year:  Vol:  Page:

This Article Full Text Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Similar articles in this journal Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Wolfrum, P. Articles by von der Malsburg, C. Search for Related Content PubMed Articles by Wolfrum, P. Articles by von der Malsburg, C.

What Is the Optimal Architecture for Visual Information Routing?

wolfrum{at}fias.uni-frankfurt.de Frankfurt Institute for Advanced Studies, D-60438 Frankfurt am Main, Germany

Christoph von der Malsburg

c.v.d.malsburg{at}fias.uni-frankfurt.de Frankfurt Institute for Advanced Studies, D-60438 Frankfurt am Main, Germany, and Computer Science Department, University of Southern California, Los Angeles, CA 90089, U.S.A.

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.

This article has been cited by other articles:

				J. Lucke, C. Keck, and C. von der Malsburg Rapid Convergence to Feature Layer Correspondences Neural Comput., October 1, 2008; 20(10): 2441 - 2463. [Abstract] [Full Text] [PDF]