Abstract
We present a simple neural network architecture which autonomously learns how to control a data driven selective attention process. In order to control the selective attention process a biologically plausible position coding is used which leads to fuzzy representations of position. An associative memory learns the connections between subsequent positions und local features. The result of presenting simple Real-World color images to the neural network architecture is shown.
supported by BMFT, Grant No. 413-5839-01 IN 101D — NAMOS-Project
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
H.-M. Gross, B. Koemer, H.J. Boehme, T. Pomüerski, “A Neural Network Hierachy for Data and Knowledge Controlled Selective Visual Attention”, Proc. of ICANN92, 1, 825–828, 1992.
H.-M. Gross, H.-J. Böhme, D. Heinke, R. Möller, T. Pomierski, “Steuerung parallel-sequentieller Verabeitungsprozesse und Strukturierung dynamischer Repräsentationen”, will be published by Springer-Verlag.
T. Pomierski, H.-M. Gross, D. Wendt, “A Distributed Multicolumnar System for Primary Cortical Analysis of Real-World Scenes”, this volume.
G.A. Carpenter, S. Grossberg, “ART2: self-organization of stable category recognition codes for analog input patterns”, Applied Optics, 26, 23, 1987.
S. Grossberg, “Some Networks That Can Learn, Remember, and Reproduce Any Number of Complicated Space-Time Pattern I”, J. of Mathematics and Mechaniscs, 19, 1, 53–91, 1969.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag London Limited
About this paper
Cite this paper
Heinke, D., Gross, HM. (1993). A Simple Selforganizing Neural Network Architecture for Selective Visual Attention. In: Gielen, S., Kappen, B. (eds) ICANN ’93. ICANN 1993. Springer, London. https://doi.org/10.1007/978-1-4471-2063-6_12
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2063-6_12
Published:
Publisher Name: Springer, London
Print ISBN: 978-3-540-19839-0
Online ISBN: 978-1-4471-2063-6
eBook Packages: Springer Book Archive