Non-linear dimensionality reduction techniques for unsupervised feature extraction

  title={Non-linear dimensionality reduction techniques for unsupervised feature extraction},
  author={Steve De Backer and Antoine Naud and Paul Scheunders},
  journal={Pattern Recognition Letters},
Dimensionality reduction techniques have been regularly used for visualization of high-dimensional data sets. In this paper, reduction to d02 is studied, with the purpose of feature extraction. Four different non-linear techniques are studied: multidimensional scaling, Sammon’s mapping, self-organizing maps and auto-associative feedforward networks. All four techniques will be presented in the same framework of optimization. A comparison with respect to feature extraction is made by evaluating… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 38 extracted citations

Improved SOM search algorithm for high-dimensional data with application to face recognition across pose and illumination

2010 International Conference of Soft Computing and Pattern Recognition • 2010
View 1 Excerpt

Piecewise one dimensional Self Organizing Map for fast feature extraction

2010 10th International Conference on Intelligent Systems Design and Applications • 2010
View 1 Excerpt


Publications referenced by this paper.
Showing 1-10 of 25 references

Decision boundary feature extraction for neural networks

IEEE Trans. Neural Networks • 1997
View 11 Excerpts
Highly Influenced

Continuous wavelets for rotation-invariant texture classification and segmentation. Unpublished

P. Vautrot, G. Van de Wouwer, P. Scheunders, S. Livens, D. Van Dyck

Continuous wavelets for rotationinvariant texture classification and segmentation

G. Van de Wouwer, P. Scheunders, D. Van Dyck
Unpublished . • 1997

r Pattern Recognition Letters 19 1998 711 – 720 720 ods in feature selection

B. D. Ripley
Pattern Recognition Letters • 1996
View 1 Excerpt

Similar Papers

Loading similar papers…