Skip to Main content Skip to Navigation
Conference papers

Optimal Feature Representation for Kernel Machines using Kernel-Target Alignment Criterion

Jean-Baptiste Pothin 1 Cédric Richard 1
1 M2S - Modélisation et Sûreté des Systèmes
ISTIT - Institut des Sciences et Technologies de l'Information de Troyes
Abstract : Kernel-target alignment is commonly used to predict the behavior of any given reproducing kernel in a classification context, without training any kernel machine. In this paper, we present a gradient ascent algorithm for maximizing the alignment over linear transform of the input space. Our method is compared to the minimization of the radius-margin bound. Experimental results on multi-dimensional benchmarks show the effectiveness of our approach.
Document type :
Conference papers
Complete list of metadatas

https://hal-utt.archives-ouvertes.fr/hal-02356442
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Friday, November 8, 2019 - 5:19:12 PM
Last modification on : Saturday, November 9, 2019 - 2:14:19 AM

Identifiers

Collections

CNRS | UTT

Citation

Jean-Baptiste Pothin, Cédric Richard. Optimal Feature Representation for Kernel Machines using Kernel-Target Alignment Criterion. 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2007, Honolulu, United States. pp.III-1065-III-1068, ⟨10.1109/ICASSP.2007.366867⟩. ⟨hal-02356442⟩

Share

Metrics

Record views

40