Hostname: page-component-cd9895bd7-gvvz8 Total loading time: 0 Render date: 2024-12-25T16:28:13.909Z Has data issue: false hasContentIssue false
  • English
  • Français

Machine-learning in astronomy

Published online by Cambridge University Press:  01 July 2015

Michael Hobson ,
Philip Graff ,
Farhan Feroz  and
Anthony Lasenby
Michael Hobson
Affiliation:
Astrophysics Group, Cavendish Laboratory, J.J. Thomson Avenue, Cambridge, CB3 0HE, UK email: [email protected], [email protected], [email protected]
Philip Graff
Affiliation:
Gravitational Astrophysics Laboratory, NASA Goddard Space Flight Center, 8800 Greenbelt Rd., Greenbelt, MD 20771, USA email: [email protected]
Farhan Feroz
Affiliation:
Astrophysics Group, Cavendish Laboratory, J.J. Thomson Avenue, Cambridge, CB3 0HE, UK email: [email protected], [email protected], [email protected]
Anthony Lasenby
Affiliation:
Astrophysics Group, Cavendish Laboratory, J.J. Thomson Avenue, Cambridge, CB3 0HE, UK email: [email protected], [email protected], [email protected]
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 methods may be used to perform many tasks required in the analysis of astronomical data, including: data description and interpretation, pattern recognition, prediction, classification, compression, inference and many more. An intuitive and well-established approach to machine learning is the use of artificial neural networks (NNs), which consist of a group of interconnected nodes, each of which processes information that it receives and then passes this product on to other nodes via weighted connections. In particular, I discuss the first public release of the generic neural network training algorithm, called SkyNet, and demonstrate its application to astronomical problems focusing on its use in the BAMBI package for accelerated Bayesian inference in cosmology, and the identification of gamma-ray bursters. The SkyNet and BAMBI packages, which are fully parallelised using MPI, are available at http://www.mrao.cam.ac.uk/software/.

Keywords

methods: data analysismethods: statisticalcosmological parametersgamma rays: bursts
Type
Contributed Papers
Information
Proceedings of the International Astronomical Union , Volume 10 , Symposium S306: Statistical Challenges in 21st Century Cosmology , May 2014 , pp. 279 - 287
Copyright
Copyright © International Astronomical Union 2015 

References

Auld, T., Bridges, M., Hobson, M. P., & Gull, S. F. 2008, MNRAS, 376, L11Google Scholar
Auld, T., Bridges, M., & Hobson, M. P. 2008, MNRAS, 387, 1575CrossRefGoogle Scholar
Ball, N. M. & Brunner, R. J. 2010, Int. J. Mod. Phys., 19, 1049CrossRefGoogle Scholar
Bliznyuk, N., et al. 2008, J. Comput. Graph. Statist., 17, 270CrossRefGoogle Scholar
Bouland, A., Easther, R., & Rosenfeld, K. 2011, J. Cosmol. Astropart. Phys., 5, 016CrossRefGoogle Scholar
Fawcett, T. 2006, Pattern Recogn. Lett., 27, 861CrossRefGoogle Scholar
Fendt, W. A. & Wandelt, B. D. 2007, ApJ, 654, 2CrossRefGoogle Scholar
Feroz, F. & Hobson, M. P. 2008, MNRAS, 384, 449Google Scholar
Feroz, F., Marshall, P. J., & Hobson, M. P. 2008, arXiv:0810.0781 [astro-ph]Google Scholar
Feroz, F., Hobson, M. P., & Bridges, M. 2009, MNRAS, 398, 1601CrossRefGoogle Scholar
Feroz, F., Hobson, M. P., Cameron, E., & Pettitt, A. N. 2013, arXiv:1306.2144 [astro-ph.IM]Google Scholar
Gehrels, N., et al. 2004, ApJ, 611, 1005Google Scholar
Graff, P., Feroz, F., Hobson, M. P., & Lasenby, A. N. 2014, MNRAS, 441, 1741CrossRefGoogle Scholar
Graff, P., Feroz, F., Hobson, M. P., & Lasenby, A. N. 2012, MNRAS, 421, 169Google Scholar
Gull, S. F. & Skilling, J. 1999, Quantified Maximum Entropy: MemSys5 Users' Manual (Maximum Entropy Data Consultants Ltd. Bury St. Edmunds, Suffolk, UK. http://www.maxent.co.uk/)Google Scholar
Higdon, D., Lawrence, E., Heitmann, K., & Habib, S. 2012, in: Feigelson, E.D. & Babu, G.J. (eds.), Statistical Chanllenges in Modern Astronomy V (New York: Springer), p. 41CrossRefGoogle Scholar
Hinton, G. E., Osindero, S., & Teh, Y.-W. 2006, Neural Comput., 18, 1527CrossRefGoogle Scholar
Hinton, G. E. & Salakhutdinov, R. R. 2006, Science, 313, 504Google Scholar
Hornik, K., Stinchcombe, M., & White, H. 1990, Neural Networks, 3, 359Google Scholar
Lewis, A. & Bridle, S. 2002, Phys. Rev. D 66 103511CrossRefGoogle Scholar
Lewis, A., Challinor, A., & Lasenby, A. N. 2000, ApJ, 538, 473CrossRefGoogle Scholar
Lien, A., Sakamoto, T., Gehrels, N., Palmer, D., & Graziani, C. 2012, Proceedings of the International Astronomical Union, 279, 347Google Scholar
MacKay, D. J. C. 1995, Network: Computation in Neural Systems, 6, 469CrossRefGoogle Scholar
MacKay, D. J. C., 2003, Information Theory, Inference, and Learning Algorithms (Cambridge: CUP)Google Scholar
Martens, J. 2010, in: Fürnkranz, J. & Joachims, T. (eds.), Proc. 27th Int. Conf. Machine Learning (Haifa: Omnipress), p. 735Google Scholar
Pearlmutter, B. A. 1994, Neural Comput., 6, 147Google Scholar
Rasmussen, C. E. 2003, in: Bernardo, J.M., Bayarri, M.J., Berger, J.O., Dawid, A.P., Heckerman, D., Smith, A.F.M., & West, M. (eds.), Bayesian statistics 7 (New York: OUP), p. 651CrossRefGoogle Scholar
Schraudolph, N. N. 2002, Neural Comput., 14, 1723Google Scholar
Skilling, J. 2004, AIP Conference Series, 735, 395Google Scholar
Tagliaferri, R.et al. 2003 Neural Networks, 16, 297CrossRefGoogle ScholarPubMed
Wanderman, D. & Piran, T. 2010, MNRAS, 406, 1944Google Scholar
Way, M. J., Scargle, J. D., Ali, K. M., & Srivastava, A. N. 2012, Advances in Machine Learning and Data Mining for Astronomy (CRC Press)Google Scholar