Dimensionality Reduction for Classification through Visualisation Using L1SNE

Lennon Cook, Junbin Gao

Research output: Book chapter/Published conference paperConference paperpeer-review

2 Citations (Scopus)

Abstract

Dimensionality Reduction algorithms have wide precedent for use in preprocessing for classification problems. This paper presents a new algorithm, based on a modification to Stochastic Neighbour Embedding and t-Distributed SNE to use the Laplacian distribution instead of, respectively, the Gaussian Distribution and a mismatched pair of the Gaussian Distribution and Student's t-Distribution. Experimental results are presented to demonstrate that this modification yields improvement.
Original languageEnglish
Title of host publicationAustralian Joint Conference on Artificial Intelligence
EditorsJiuyong Li
Place of PublicationGermany
PublisherSpringer
Pages204-212
Number of pages9
Publication statusPublished - 2010
EventAI 2010 23rd conference - Adelaide, SA, Australia
Duration: 07 Dec 201010 Dec 2010

Conference

ConferenceAI 2010 23rd conference
CountryAustralia
Period07/12/1010/12/10

Fingerprint Dive into the research topics of 'Dimensionality Reduction for Classification through Visualisation Using L1SNE'. Together they form a unique fingerprint.

Cite this