Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

A study on multi-scale kernel optimisation via centered kernel-target alignment

Perez-Ortiz, M., Gutierrez, P. A., Sanchez-Monedero, Javier and Hervas-Martinez, C. 2016. A study on multi-scale kernel optimisation via centered kernel-target alignment. Neural Processing Letters 44 (2) , pp. 491-517. 10.1007/s11063-015-9471-0

[img]
Preview
PDF - Accepted Post-Print Version
Download (1MB) | Preview

Abstract

Kernel mapping is one of the most widespread approaches to intrinsically deriving nonlinear classifiers. With the aim of better suiting a given dataset, different kernels have been proposed and different bounds and methodologies have been studied to optimise them. We focus on the optimisation of a multi-scale kernel, where a different width is chosen for each feature. This idea has been barely studied in the literature, although it has been shown to achieve better performance in the presence of heterogeneous attributes. The large number of parameters in multi-scale kernels makes it computationally unaffordable to optimise them by applying traditional cross-validation. Instead, an analytical measure known as centered kernel-target alignment (CKTA) can be used to align the kernel to the so-called ideal kernel matrix. This paper analyses and compares this and other alternatives, providing a review of the literature in kernel optimisation and some insights into the usefulness of multi-scale kernel optimisation via CKTA. When applied to the binary support vector machine paradigm (SVM), the results using 24 datasets show that CKTA with a multi-scale kernel leads to the construction of a well-defined feature space and simpler SVM models, provides an implicit filtering of non-informative features and achieves robust and comparable performance to other methods even when using random initialisations. Finally, we derive some considerations about when a multi-scale approach could be, in general, useful and propose a distance-based initialisation technique for the gradient-ascent method, which shows promising results.

Item Type: Article
Date Type: Publication
Status: Published
Schools: Journalism, Media and Culture
Publisher: Springer Verlag
ISSN: 1370-4621
Date of First Compliant Deposit: 5 July 2018
Last Modified: 28 Jun 2019 05:45
URI: http://orca.cf.ac.uk/id/eprint/112796

Citation Data

Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics