Finding disentangled representations using VAE

Bachelor thesis (2021)

Authors

R. d'Anjou Electrical Engineering, Mathematics and Computer Science

Contributors

S. Makrodimitris Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
T.R.M. Abdelaal Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
M. Charrout Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
M.A.M.E. Eltager Pattern Recognition and Bioinformatics - EEMCS (supervisor 1)
E. Isufi (supervisor 2)
M.J.T. Reinders Pattern Recognition and Bioinformatics - EEMCS (supervisor 2)
Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright: © 2021 Raymond d'Anjou
Deep learning VAE Biological processes
More Info
expand_more

Published Date

02-07-2021

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

This study presents a comparison of different VariationalAutoencoder(VAE) models to see which VAE models arebetter at finding disentangled representations. Specificallytheir ability to encode biological processes into distinct la-tent dimensions. The biological processes that will be lookedat are the cell cycle and differentiation state. The cell cycleis expressed as a S- and G2M-Score and the differentiationstate is expressed as a number that quantifies the develop-ment time of the cells. First the models will be trained, afterthat the models will be evaluated. The evaluation is doneby checking the latent dimensions for a correlation with thetwo aforementioned biological processes. From this it be-came quite clear that VAE and DIP-VAE performed theworst out of the four models tested. On the other handβ-VAE andβ-TCVAE performed by far the best.