Galaxy morphology classification using neural ordinary differential equations

Gupta, R. and Srijith, P K and Desai, Shantanu (2022) Galaxy morphology classification using neural ordinary differential equations. Astronomy and Computing, 38. p. 100543. ISSN 2213-1337

[img] Text
Astronomy_and_Computing.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB)

Abstract

We introduce a continuous depth version of the Residual Network (ResNet) called Neural ordinary differential equations (NODE) for the purpose of galaxy morphology classification. We carry out a classification of galaxy images from the Galaxy Zoo 2 dataset, consisting of five distinct classes, and obtained an accuracy between 91%–95%, depending on the image class. We train NODE with different numerical techniques such as adjoint and Adaptive Checkpoint Adjoint (ACA) and compare them against ResNet. While ResNet has certain drawbacks, such as time consuming architecture selection (e.g. the number of layers) and the requirement of a large dataset needed for training, NODE can overcome these limitations. Through our results, we show that the accuracy of NODE is comparable to ResNet, and the number of parameters used is about one-third as compared to ResNet, thus leading to a smaller memory footprint, which would benefit next generation surveys. © 2022 Elsevier B.V.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Srijith, P Khttps://orcid.org/0000-0002-2820-0835
Desai, Shantanuhttp://orcid.org/0000-0002-0466-3288
Item Type: Article
Additional Information: We would like to thank the galaxy challenge, Galaxy Zoo, SDSS and Kaggle platform for sharing their data. RG is supported by funding from DST-ICPS (T-641). We are grateful to the anonymous referee for useful feedback on our manuscript.
Uncontrolled Keywords: Galaxy morphology classification; Neural ordinary differential equations; ResNets
Subjects: Computer science
Physics
Physics > Astronomy Astrophysics
Divisions: Department of Computer Science & Engineering
Department of Physics
Depositing User: . LibTrainee 2021
Date Deposited: 27 Jul 2022 07:11
Last Modified: 27 Jul 2022 07:11
URI: http://raiith.iith.ac.in/id/eprint/9946
Publisher URL: http://doi.org/10.1016/j.ascom.2021.100543
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 9946 Statistics for this ePrint Item