Subspace Dimension Selection and Averaged Learning Subspace Method in Handwritten Digit Classification

Jorma Laaksonen, Erkki OjaICANN 1996 · OpenReview

Abstract

We present recent improvements in using subspace classifiers in recognition of handwritten digits. Both non-trainable CLAFIC and trainable ALSM methods are used with four models for initial selection of subspace dimensions and their further error-driven refinement. The results indicate that these additions to the subspace classification scheme noticeably reduce the classification error.
BibTeX
@inproceedings{laaksonen1996subspace,
  author = {Jorma Laaksonen and Erkki Oja},
  title = {{Subspace Dimension Selection and Averaged Learning Subspace Method in Handwritten Digit Classification}},
  booktitle = {ICANN},
  year = {1996},
  url = {https://openreview.net/forum?id=uKfsNZhMY4},
}

Loading related content...

Figure