Parallel Projections for Manifold Learning

Harry Strange, Reyer Zwiggelaar

Research output: Contribution to conferencePaper

1 Citation (SciVal)

Abstract

Manifold learning is a widely used statistical tool which reduces the dimensionality of a data set while aiming to maintain both local and global properties of the data. We present a novel manifold learning technique which aligns local hyperplanes to build a global representation of the data. A Minimum Spanning Tree provides the skeleton needed to traverse the manifold so that the local hyperplanes can be merged using parallel projections to build a global hyperplane of the data. We show state of the art results when compared against existing manifold learning algorithm on both artificial and real world image data.
Original languageEnglish
Publication statusPublished - 2010

Fingerprint

Dive into the research topics of 'Parallel Projections for Manifold Learning'. Together they form a unique fingerprint.

Cite this