Neural networks letter: LAGO on the unit sphere

Authors:
Alexandra Laflamme-Sanders;Mu Zhu
Affiliations:
University of Waterloo, Waterloo, Ontario, Canada N2L 3G1;University of Waterloo, Waterloo, Ontario, Canada N2L 3G1
Venue:
Neural Networks
Year:
2008

Citing 6
Cited 0

Term-weighting approaches in automatic text retrieval

Information Processing and Management: an International Journal
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
Latent Semantic Kernels

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Augmenting Naive Bayes Classifiers with Statistical Language Models

Information Retrieval
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
Mismatch string kernels for discriminative protein classification

Bioinformatics

Quantified Score

Hi-index	0.01

Visualization

Abstract

LAGO is an efficient kernel algorithm designed specifically for the rare target detection problem. However, unlike other kernel algorithms, LAGO cannot be easily used with many domain-specific kernels. We solve this problem by first providing a unified framework for LAGO and clarifying its basic principle, and then applying that principle on the unit sphere instead of in the Euclidean space.