28 September 2016 Deep learning classifier based on NPCA and orthogonal feature selection
Author Affiliations +
Proceedings Volume 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016; 100315E (2016) https://doi.org/10.1117/12.2249848
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, 2016, Wilga, Poland
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).
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Stanisław Jankowski, Zbigniew Szymański, Uladzimir Dziomin, Vladimir Golovko, Aleksy Barcz, "Deep learning classifier based on NPCA and orthogonal feature selection", Proc. SPIE 10031, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2016, 100315E (28 September 2016); doi: 10.1117/12.2249848; https://doi.org/10.1117/12.2249848
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Neural network with a predetermined activity dynamics
Proceedings of SPIE (December 07 1994)
Nonlinear features for improved pattern recognition
Proceedings of SPIE (July 06 2001)
Fuzzy recognition of noncompact musical objects
Proceedings of SPIE (March 27 1997)

Back to Top