DocumentCode
1032900
Title
Node compression in simulated annealing networks: an investigation with a scene analysis benchmark
Author
Tambouratzis, Tatiana
Author_Institution
Inst. of Inf. & Telecommun., NRCPS Demokritos, Athens
Volume
30
Issue
4
fYear
1994
fDate
2/17/1994 12:00:00 AM
Firstpage
334
Lastpage
336
Abstract
Harmony theory (HT) networks constitute simulated annealing networks which greatly benefit from sparse coding: the precision and cooling procedure of the network improve: however, the increase in size renders each network update slow and computationally expensive. The author examines node compression. Comparisons with a sparse HT network are made, using as a benchmark a scene analysis task
Keywords
image coding; image recognition; neural nets; simulated annealing; complex constraint propagation problems; cooling procedure; harmony theory networks; node compression; scene analysis benchmark; simulated annealing networks; sparse coding;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
DOI
10.1049/el:19940214
Filename
267316
Link To Document