Javascript must be enabled for the correct page display

Graph Layouts by t-distributed Stochastic Neighbour Embedding

Kruiger, J.F. (2016) Graph Layouts by t-distributed Stochastic Neighbour Embedding. Master's Thesis / Essay, Computing Science.

[img]
Preview
Text
msc_thesis_han_v2.pdf - Published Version

Download (9MB) | Preview
[img] Text
Toestemming.pdf - Other
Restricted to Backend only

Download (145kB)

Abstract

In this thesis, the use of the t-distributed Stochastic Neighbour Embedding (t-SNE) multidimensional projection technique for producing graph layouts is evaluated. t-SNE is typically used for visualizing high-dimensional data as two- or three-dimensional scatter plots. In our work, graphs are represented as high-dimensional datasets, and are projected to two-dimensional layouts using a suitably adapted t-SNE method. The novel graph layouts are visually compared with layouts obtained by current state-of-the-art methods. The comparison shows positive results that support the suitability claim of using t-SNE for producing graph layouts.

Item Type: Thesis (Master's Thesis / Essay)
Degree programme: Computing Science
Thesis type: Master's Thesis / Essay
Language: English
Date Deposited: 15 Feb 2018 08:25
Last Modified: 15 Feb 2018 08:25
URI: http://fse.studenttheses.ub.rug.nl/id/eprint/14540

Actions (login required)

View Item View Item