LATENT REPRESENTATIONS OF GALAXY IMAGES WITH AUTOENCODERS
Huang, ChenYang
Loading…
Permalink
https://hdl.handle.net/2142/125089
Description
Title
LATENT REPRESENTATIONS OF GALAXY IMAGES WITH AUTOENCODERS
Author(s)
Huang, ChenYang
Issue Date
2020-05-01
Keyword(s)
data analysis; statistical method; astronomy; image processing; machine learning
Abstract
This study presents a way to represent galaxy images in a low-dimension space by compressing them into “latent variables” with Autoencoders and how this method can be used in a series of applications. To further measure the performance of the encoding, a pipeline is set up to take a list of measurements including MSE of the original data and the reconstruction from the latent variables, MSE of the original label data and the recovery from the latent variables. Next, we will demonstrate three applications of the latent variables: similarity search, outlier detection and unsupervised clustering.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
