Galaxy Morphology Classification using Neural Ordinary Differential Equations

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.

arXiv comment10 pages, 5 figures. Now also used NODE_ACA. Accepted for publication in Astronomy and Computing

References in corpus (47)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• The Sloan Digital Sky Survey: Technical Summary
• Star Formation in Galaxies Along the Hubble Sequence
• The Seventh Data Release of the Sloan Digital Sky Survey
• Deep Residual Learning for Image Recognition
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
• LSST Science Book, Version 2.0
• The Relationship Between Stellar Light Distributions of Galaxies and their Formation Histories
• A New Non-Parametric Approach to Galaxy Morphological Classification
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Galaxy Zoo 2: detailed morphological classifications for 304,122 galaxies from the Sloan Digital Sky Survey
• Galaxy Zoo: the dependence of morphology and colour on environment
• Neural Ordinary Differential Equations
• The DEEP Groth Strip Survey II. Hubble Space Telescope Structural Parameters of Galaxies in the Groth Strip
• Data Mining and Machine Learning in Astronomy
• The Mass Assembly Histories of Galaxies of Various Morphologies in the GOODS Fields
• Angular momentum and galaxy formation revisited
• Galaxy Zoo: Disentangling the Environmental Dependence of Morphology and Colour
• Galaxy Zoo: A sample of blue early-type galaxies at low redshift
• Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
• Astrophysically Motivated Bulge-Disk Decompositions of SDSS Galaxies
• Machine Learning in Astronomy: a practical overview
• Galaxy Morphology Classification with Deep Convolutional Neural Networks
• Galaxy Zoo: Quantitative Visual Morphological Classifications for 48,000 galaxies from CANDELS
• Big Universe, Big Data: Machine Learning and Image Analysis for Astronomy
• Galaxies, Human Eyes and Artificial Neural Networks
• Machine and Deep Learning Applied to Galaxy Morphology -- A Comparative Study
• New Image Statistics for Detecting Disturbed Galaxy Morphologies at High Redshift
• Galaxy Zoo: Morphological Classifications for 120,000 Galaxies in HST Legacy Imaging
• Wide-Field InfraRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA Final Report
• Galaxy morphological classification in deep-wide surveys via unsupervised machine learning
• ANODE: Unconditionally Accurate Memory-Efficient Gradients for Neural ODEs
• The Morphological Evolution of Galaxies
• Separation of pulsar signals from noise with supervised machine learning algorithms
• Augmented Neural ODEs
• Beyond Spheroids and Discs: Classifications of CANDELS Galaxy Structure at 1.4 < z < 2 via Principal Component Analysis
• AstroVaDEr: Astronomical Variational Deep Embedder for Unsupervised Morphological Classification of Galaxies and Synthetic Image Generation
• Deep Learning at Scale for the Construction of Galaxy Catalogs in the Dark Energy Survey
• Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE
• Explaining deep learning of galaxy morphology with saliency mapping
• Galaxy classification: deep learning on the OTELO and COSMOS databases
• Deep learning for studies of galaxy morphology
• MRI Image Reconstruction via Learning Optimization Using Neural ODEs
• Neural ODE with Temporal Convolution and Time Delay Neural Networks for Small-Footprint Keyword Spotting
• Neural ODEs for Image Segmentation with Level Sets

Cited by in corpus (10)

• Classifying Galaxy Morphologies with Few-Shot Learning
• Unsupervised Galaxy Morphological Visual Representation with Deep Contrastive Learning
• Deep Learning Assessment of galaxy morphology in S-PLUS DataRelease 1
• Identifying outliers in astronomical images with unsupervised machine learning
• Galaxy Morphology Classification Using Multi-Scale Convolution Capsule Network
• Enhanced Astronomical Source Classification with Integration of Attention Mechanisms and Vision Transformers
• Lessons Learned from the Two Largest Galaxy Morphological Classification Catalogues built by Convolutional Neural Networks
• Galaxy Image Classification using Hierarchical Data Learning with Weighted Sampling and Label Smoothing
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Galaxy Morphological Classification with Efficient Vision Transformer