DocumentCode :
285204
Title :
Dynamic selection through gating lattices
Author :
Postma, Eric O. ; Van den Herik, H. Jaap ; Hudson, Patrick T W
Author_Institution :
Dept. of Comput. Sci., Limburg Univ., Maastricht, Netherlands
Volume :
3
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
786
Abstract :
The authors introduce the gating lattice as a parallel distributed model for adaptive sampling of visual images. A gating lattice is a parallel switch capable of dynamic gating, i.e., selecting and propagating one of several input patterns. Gating is distributed in that it is locally controlled. An example of a dynamic-selection problem is given, and the appropriate gating lattice is introduced. The equivalence of the gating lattice with the Ising lattice is specified. Simulations have led to the conclusion that gating lattices form an adequate substrate for models of visual attention
Keywords :
image processing; neural nets; Ising lattice; adaptive sampling; gating lattice; parallel distributed model; visual attention; visual images; Computer science; Image sampling; Large-scale systems; Lattices; Layout; Neurons; Retina;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227056
Filename :
227056
Link To Document :
بازگشت