University of Illinois Urbana-Champaign

Latent representations of galaxy images with autoencoders

Huang, Chenyang

Content Files
SP20-ECE499-Thesis-Huang, Chenyang.pdf

Permalink

https://hdl.handle.net/2142/107275

Description

Title
Latent representations of galaxy images with autoencoders
Author(s)
Huang, Chenyang
Contributor(s)
Zhao, Zhizhen
Issue Date
2020-05
Keyword(s)
  • data analysis
  • statistical method
  • astronomy
  • image processing
  • machine learning
Date of Ingest
2020-06-12T19:27:36Z
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.
Type of Resource
text
Genre of Resource
other
Language
en
Permalink
http://hdl.handle.net/2142/107275

Owning Collections

Senior Theses - Electrical and Computer Engineering PRIMARY
The best of ECE undergraduate research