DocumentCode
353267
Title
Improved ψ-APEX algorithm for digital image compression
Author
Fiori, Simone ; Costa, Saverio ; Burrascano, Pietro
Author_Institution
Dept. of Ind. Eng., Perugia Univ., Italy
Volume
3
fYear
2000
fDate
2000
Firstpage
392
Abstract
In this work we derive an improvement of ψ-APEX (adaptive principal component extractor) neural algorithms, based on a laterally-connected neural architecture, which arises from an optimization theory specialized for this topology. Such a class contains, as a special case, an APEX-like algorithm, but it also contains a subclass of algorithms that show interesting convergence features when compared with the original one
Keywords
adaptive signal processing; data compression; image coding; neural net architecture; optimisation; principal component analysis; ψ-APEX principal component analysis neural algorithms; PCA; adaptive principal component extractor; convergence features; digital image compression; laterally-connected neural architecture; optimization theory; Convergence; Covariance matrix; Digital images; Eigenvalues and eigenfunctions; Image coding; Joining processes; Network topology; Neural networks; Neurons; Unsupervised learning;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location
Como
ISSN
1098-7576
Print_ISBN
0-7695-0619-4
Type
conf
DOI
10.1109/IJCNN.2000.861336
Filename
861336
Link To Document