On Feature Extraction Capabilities of Fast Orthogonal Neural Networks

  • Bartłomiej Stasiak
  • Mykhaylo Yatsymirskyy
Conference paper

DOI: 10.1007/978-3-540-71629-7_4

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4432)
Cite this paper as:
Stasiak B., Yatsymirskyy M. (2007) On Feature Extraction Capabilities of Fast Orthogonal Neural Networks. In: Beliczynski B., Dzielinski A., Iwanowski M., Ribeiro B. (eds) Adaptive and Natural Computing Algorithms. ICANNGA 2007. Lecture Notes in Computer Science, vol 4432. Springer, Berlin, Heidelberg

Abstract

The paper investigates capabilities of fast orthogonal neural networks in a feature extraction task for classification problems. Neural networks with an architecture based on the fast cosine transform, type II and IV are built and applied for extraction of features used as a classification base for a multilayer perceptron. The results of the tests show that adaptation of the neural network allows to obtain a better transform in the feature extraction sense as compared to the fast cosine transform. The neural implementation of both the feature extractor and the classifier enables integration and joint learning of both blocks.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Bartłomiej Stasiak
    • 1
  • Mykhaylo Yatsymirskyy
    • 1
  1. 1.Institute of Computer Science, Technical University of Łódź, ul. Wólczańska 215, 93-005 ŁódźPoland

Personalised recommendations