Title
An Analog VLSI Pulsed Neural Network for Image Segmentation Using Adaptive Connection Weights
Abstract
An analog VLSI pulsed neural network for image segmentation using adaptive connection weights is presented. The network marks segments in the image through synchronous firing patterns. The synchronization is achieved through adaption of connection weights. The adaption uses only local signals in a data-driven and self-organizing way. It is shown that for the proposed adaption rules a simple analog VLSI implementation is feasible due to the required local connections and the data-driven self-organizing approach.
Year
DOI
Venue
2002
10.1007/3-540-46084-5_209
ICANN
Keywords
Field
DocType
image segmentation,adaptive connection weight,network marks segment,connection weight,neural network,analog vlsi,local signal,analog vlsi pulsed neural,adaptive connection weights,proposed adaption rule,data-driven self-organizing approach,vlsi implementation,self organization
Computer vision,Synchronization,Pattern recognition,Adaptive method,Computer science,Self-organization,Image processing,Image segmentation,Artificial intelligence,Artificial neural network,Very-large-scale integration,Machine learning
Conference
Volume
ISSN
ISBN
2415
0302-9743
3-540-44074-7
Citations 
PageRank 
References 
4
0.62
2
Authors
5
Name
Order
Citations
PageRank
Arne Heittmann1245.94
Ulrich Ramacher219528.69
Daniel Matolin323221.01
Jörg Schreiter492.38
René Schüffny513324.49