pith. sign in

arxiv: 2012.07735 · v2 · pith:EO6RM3PHnew · submitted 2020-12-14 · 🌌 astro-ph.IM · astro-ph.GA

Galaxy Morphology Classification using Neural Ordinary Differential Equations

classification 🌌 astro-ph.IM astro-ph.GA
keywords resnetgalaxynodeclassificationaccuracyadjointdatasetdifferential
0
0 comments X
read the original 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 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.