Hostname: page-component-78c5997874-g7gxr Total loading time: 0 Render date: 2024-11-10T14:25:19.879Z Has data issue: false hasContentIssue false
  • English
  • Français

Galaxy Classifications with Deep Learning

Published online by Cambridge University Press:  30 May 2017

Vesna Lukic  and
Marcus Brüggen
Vesna Lukic
Affiliation:
Hamburger Sternwarte, University of Hamburg, Gojenbergsweg 112, 21029, Hamburg, Germany email: Vesna.Lukic@hs.uni-hamburg.de, Marcus.Brueggen@hs.uni-hamburg.de
Marcus Brüggen
Affiliation:
Hamburger Sternwarte, University of Hamburg, Gojenbergsweg 112, 21029, Hamburg, Germany email: Vesna.Lukic@hs.uni-hamburg.de, Marcus.Brueggen@hs.uni-hamburg.de
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

Machine learning techniques have proven to be increasingly useful in astronomical applications over the last few years, for example in object classification, estimating redshifts and data mining. One example of object classification is classifying galaxy morphology. This is a tedious task to do manually, especially as the datasets become larger with surveys that have a broader and deeper search-space. The Kaggle Galaxy Zoo competition presented the challenge of writing an algorithm to find the probability that a galaxy belongs in a particular class, based on SDSS optical spectroscopy data. The use of convolutional neural networks (convnets), proved to be a popular solution to the problem, as they have also produced unprecedented classification accuracies in other image databases such as the database of handwritten digits (MNIST †) and large database of images (CIFAR ‡). We experiment with the convnets that comprised the winning solution, but using broad classifications. The effect of changing the number of layers is explored, as well as using a different activation function, to help in developing an intuition of how the networks function and to see how they can be applied to radio galaxy images.

Keywords

Galaxy morphologydeep learningclassificationsdeep neural networks
Type
Contributed Papers
Information
Proceedings of the International Astronomical Union , Volume 12 , Symposium S325: Astroinformatics , October 2016 , pp. 217 - 220
Copyright
Copyright © International Astronomical Union 2017 

References

Dieleman, S., Willett, K. W., & Dambre, J. 2015, Mon. Not. R. Astron. Soc., 000, 1–20 Google Scholar
Willett, K. W. 2016, Proceedings of Science Google Scholar
He, K., Zhang, X., Ren, S., & Sun, J. 2015, Microsoft Research Google Scholar
Glorot, X. & Bengio, Y. 2010, JMLR W&CP, 9:249–256Google Scholar
Glorot, X., Bordes, A., & Bengio, Y. 2011, JMLR W&CP, 15:315–323Google Scholar
Giavalisco, M. 2006, IOP Publishing Ltd Google Scholar
Whittam, I. 2016, Huffington post http://www.huffingtonpost.com/the-conversation-africa/radio-galaxies-the-myster_b_12554818.html Google Scholar
Willett, K. W., Lintott, C. J., & Bamford, S. P., et al. 2013, Mon. Not. R. Astron. Soc., 000, 1–29 Google Scholar
Nielsen, M. A. 2015, Determination Press Google Scholar
Karpathy, A. 2016, CS231n Convolutional Neural Networks for Visual Recognition http://cs231n.github.io/convolutional-networks//#overview Google Scholar
Alger, M. 2016, PhD Thesis Google Scholar
Gu, J., Wang, Z., & Kuen, J., et al. 2016, arXiv:1512.07108 [cs.CV] Google Scholar
Krizhevsky, A, et al. 2012, Advances in Neural Information Processing Systems 25 Google Scholar
Fanaroff, B. & Riley, J. 1974, Mon. Not. R. Astron. Soc. Google Scholar