A comparative study of neural network based feature extraction paradigms

Research output: Contribution to journalArticlepeer-review

68 Scopus citations


The projection maps and derived classification accuracies of a neural network (NN) implementation of Sammon's mapping, an auto-associative NN (AANN) and a multilayer perceptron (MLP) feature extractor are compared with those of the conventional principal component analysis (PCA). Tested on five real-world database, the MLP provides the highest classification accuracy at the cost of deforming the data structure, whereas the linear models preserve the structure but usually with inferior accuracy.

Original languageEnglish
Pages (from-to)7-14
Number of pages8
JournalPattern Recognition Letters
Issue number1
StatePublished - 1 Jan 1999


  • Auto-associative neural network
  • Classification
  • Data projection
  • Feature extraction
  • Multilayer perceptron
  • Principal components
  • Sammon's mapping

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'A comparative study of neural network based feature extraction paradigms'. Together they form a unique fingerprint.

Cite this