Deep learning classifier based on NPCA and orthogonal feature selection

Stanisław Jankowski , Zbigniew Szymański , Uladzimir Dziomin , Vladimir Golovko , Aleksy Stanisław Barcz

Abstract

In this paper the idea of deep learning classifier is developed. The effectiveness of discriminative classifier, as e.g. multilayer perceptron, support vector machine can be improved by adding the data preprocessing blocks: orthogonal feature selection (Gram-Schmidt method) and nonlinear principal component analysis. We present the case study of various structures of deep learning systems (scenarios).
Author Stanisław Jankowski ISE
Stanisław Jankowski,,
- The Institute of Electronic Systems
, Zbigniew Szymański II
Zbigniew Szymański,,
- The Institute of Computer Science
, Uladzimir Dziomin
Uladzimir Dziomin,,
-
, Vladimir Golovko
Vladimir Golovko,,
-
, Aleksy Stanisław Barcz ISE
Aleksy Stanisław Barcz,,
- The Institute of Electronic Systems
Pages 100315E-1- 100315E-9
Publication size in sheets0.5
Book Romaniuk Ryszard (eds.): Proc. SPIE. 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, vol. 10031, 2016, SPIE , ISBN 9781510604858, [781510604865 (electronic) ], 1170 p., DOI:10.1117/12.2257157
Keywords in English NPCA, neural network classifier, feature selection,Gram-Schmidt orthogonalization, deep learning
DOIDOI:10.1117/12.2249848
URL http://dx.doi.org.spiedl.eczyt.bg.pw.edu.pl/10.1117/12.2249848
projectDevelopment of new algorithms in the areas of software and computer architecture, artificial intelligence and information systems and computer graphics . Project leader: Rybiński Henryk, , Phone: +48 22 234 7731, start date 18-05-2015, end date 30-11-2016, II/2015/DS/1, Completed
WEiTI Działalność statutowa
Languageen angielski
File
100315E_jankowski2.pdf 489.39 KB
Score (nominal)15
ScoreMinisterial score = 15.0, 27-03-2017, BookChapterMatConf
Ministerial score (2013-2016) = 15.0, 27-03-2017, BookChapterMatConf
Citation count*0 (2018-06-18)
Cite
Share Share

Get link to the record
msginfo.png


* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Back