Adaptive kernel matching pursuit for pattern classification

POPOVICI, Vlad a JP THIRAN. Adaptive kernel matching pursuit for pattern classification. In Hamza, MH. PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND APPLICATIONS, VOLS 1AND 2. CALGARY: ACTA PRESS, 2004, s. 235-239.

Základní údaje

Originální název

Adaptive kernel matching pursuit for pattern classification

Autoři

POPOVICI, Vlad a JP THIRAN

Vydání

CALGARY, PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND APPLICATIONS, VOLS 1AND 2, od s. 235-239, 5 s. 2004

Nakladatel

ACTA PRESS

---

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Utajení

není předmětem státního či obchodního tajemství

Označené pro přenos do RIV

Ne

UT WoS

000228622100041

Klíčová slova anglicky

pattern recognition; kernel matching pursuit; sparse classifiers

---

Anotace

V originále

A sparse classifier is guaranteed to generalize better than a denser one, given they perform identical on the training set. However, methods like Support Vector Machine, even if they produce relatively sparse models, are known to scale linearly as the number of training examples increases. A recent proposed method, the Kernel Matching Pursuit, presents a number of advantages over the SVM, like sparser solutions and faster training. In this paper we present an extension of the KMP in which we prove that adapting the dictionary to the data results in improved performances. We discuss different techniques for dictionary adaptation and present some results on standard datasets.