ICANN ’93 pp 63-66 | Cite as

A Simple Selforganizing Neural Network Architecture for Selective Visual Attention

  • D. Heinke
  • H.-M. Gross
Conference paper

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.

Keywords

Convolution Pyramid 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    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.Google Scholar
  2. [2]
    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.Google Scholar
  3. [3]
    T. Pomierski, H.-M. Gross, D. Wendt, “A Distributed Multicolumnar System for Primary Cortical Analysis of Real-World Scenes”, this volume.Google Scholar
  4. [4]
    G.A. Carpenter, S. Grossberg, “ART2: self-organization of stable category recognition codes for analog input patterns”, Applied Optics, 26, 23, 1987.CrossRefGoogle Scholar
  5. [5]
    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.MathSciNetMATHGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • D. Heinke
    • 1
  • H.-M. Gross
    • 1
  1. 1.Division of NeuroinformaticsTechnical University of IlmenauIlmenauGermany

Personalised recommendations