Please use this identifier to cite or link to this item:
Title: Invariant template matching in systems with spatiotemporal coding: A matter of instability
Authors: Tyukin, Ivan Yu.
Tyukina, Tatiana
van Leeuwen, Cees
First Published: May-2009
Publisher: Elsevier
Citation: Neural Networks, 2009, 22 (4), pp. 425-449.
Abstract: We consider the design principles of algorithms that match templates to images subject to spatiotemporal encoding. Both templates and images are encoded as temporal sequences of samplings from spatial patterns. Matching is required to be tolerant to various combinations of image perturbations. These include ones that can be modeled as parameterized uncertainties such as image blur, luminance, and, as special cases, invariant transformation groups such as translation and rotations, as well as unmodeled uncertainties (noise). For a system to deal with such perturbations in an efficient way, they are to be handled through a minimal number of channels and by simple adaptation mechanisms. These normative requirements can be met within the mathematical framework of weakly attracting sets. We discuss explicit implementation of this principle in neural systems and show that it naturally explains a range of phenomena in biological vision, such as mental rotation, visual search, and the presence of multiple time scales in adaptation. We illustrate our results with an application to a realistic pattern recognition problem.
DOI Link: 10.1016/j.neunet.2009.01.014
ISSN: 0893-6080
Type: Article
Rights: This is the author's final draft of the paper published as Neural Networks, 2009, 22 (4), pp. 425-449. The final version is available from Doi: 10.1016/j.neunet.2009.01.014
Appears in Collections:Published Articles, Dept. of Mathematics

Files in This Item:
File Description SizeFormat 
Adaptive_visual_system.pdf1.16 MBAdobe PDFView/Open

Items in LRA are protected by copyright, with all rights reserved, unless otherwise indicated.