Feature subspace SVMs (FS-SVMs) for high dimensional handwritten digit recognition (Q1046605)

From MaRDI portal
scientific article
Language Label Description Also known as
English
Feature subspace SVMs (FS-SVMs) for high dimensional handwritten digit recognition
scientific article

    Statements

    Feature subspace SVMs (FS-SVMs) for high dimensional handwritten digit recognition (English)
    0 references
    0 references
    0 references
    22 December 2009
    0 references
    Summary: Training SVMs on high dimensional feature vectors in one shot incurs high computational cost. A low dimensional representation reduces computational overhead and improves the classification speed. Low dimensionality also reduces the risk of over-fitting and tends to improve the generalisation ability of classification algorithms. For many important applications, the dimensionality may remain prohibitively high despite feature selection. In this paper, we address these issues primarily in the context of handwritten digit data. In particular, we make the following contributions: (1) we introduce the \(\alpha \)-minimum feature over (\(\alpha \)-MFC) problem and prove it to be NP-hard; (2) investigate the efficacy of a divide-and-conquer ensemble method for SVMs based on segmentation of the feature space (FS-SVMs); 3) propose a greedy algorithm for finding an approximate \(\alpha \)-MFC using FS-SVMs.
    0 references
    dimensionality reduction
    0 references
    classification
    0 references
    greedy algorithms
    0 references
    support vector machines
    0 references
    SVMs
    0 references
    approximation algorithms
    0 references
    feature selection
    0 references
    feature subspace
    0 references
    handwritten digits
    0 references
    digit recognition
    0 references
    handwriting
    0 references

    Identifiers