Galaxy morphology classification using neural ordinary differential equations
ASTRONOMY AND COMPUTING(2022)
摘要
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. (C)& nbsp;2022 Elsevier B.V. All rights reserved.
更多查看译文
关键词
Neural ordinary differential equations, Galaxy morphology classification, ResNets
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络