Galaxy Zoo: probabilistic morphology through Bayesian CNNs and active learning
Mike Walmsley,Lewis Smith,Chris Lintott,Yarin Gal,Steven P. Bamford,Hugh Dickinson,Lucy Fortson,Sandor Kruk,Karen L. Masters,Karen L. Masters,Claudia Scarlata,Brooke Simmons,Brooke Simmons,Rebecca Smethurst,Darryl Wright +14 more
Reads0
Chats0
TLDR
By combining human and machine intelligence, Galaxy Zoo will be able to classify surveys of any conceivable scale on a timescale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.Abstract:
We use Bayesian convolutional neural networks and a novel generative model of Galaxy Zoo volunteer responses to infer posteriors for the visual morphology of galaxies. Bayesian CNN can learn from galaxy images with uncertain labels and then, for previously unlabelled galaxies, predict the probability of each possible label. Our posteriors are well-calibrated (e.g. for predicting bars, we achieve coverage errors of 11.8 per cent within a vote fraction deviation of 0.2) and hence are reliable for practical use. Further, using our posteriors, we apply the active learning strategy BALD to request volunteer responses for the subset of galaxies which, if labelled, would be most informative for training our network. We show that training our Bayesian CNNs using active learning requires up to 35–60 per cent fewer labelled galaxies, depending on the morphological feature being classified. By combining human and machine intelligence, Galaxy zoo will be able to classify surveys of any conceivable scale on a time-scale of weeks, providing massive and detailed morphology catalogues to support research into galaxy evolution.read more
Citations
More filters
Journal ArticleDOI
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
Moloud Abdar,Farhad Pourpanah,Sadiq Hussain,Dana Rezazadegan,Li Liu,Mohammad Ghavamzadeh,Paul Fieguth,Xiaochun Cao,Abbas Khosravi,U. Rajendra Acharya,U. Rajendra Acharya,U. Rajendra Acharya,Vladimir Makarenkov,Saeid Nahavandi +13 more
TL;DR: This study reviews recent advances in UQ methods used in deep learning and investigates the application of these methods in reinforcement learning (RL), and outlines a few important applications of UZ methods.
Overview of the DESI Legacy Imaging Surveys
David J. Schlegel,Jacqueline Beechert,Kaylan J. Burleigh,Arjun Dey,Joseph R. Findlay,David Herrera,Stéphanie Juneau,Martin Landriau,Dustin Lang,Aaron M. Meisner,John Moustakas,Adam D. Myers,Edward F. Schlafly,F. Valdes,Benjamin A. Weaver,Jinyi Yang,Christophe Yèche +16 more
TL;DR: The DESI Legacy Imaging Surveys (http://legacysurvey.org/) project is a combination of three public projects (the Dark Energy Camera Legacy Survey, the Beijing-Arizona Sky Survey, and the Mayall z-band Legacy Survey) that will jointly image ≈14,000 deg2 of the extragalactic sky visible from the northern hemisphere in three optical bands (g, r, and z) using telescopes at the Kitt Peak National Observatory and the Cerro Tololo Inter-American Observatory.
Journal ArticleDOI
Machine-learning methods for computational science and engineering
TL;DR: This paper explores the ability of ML to produce computationally efficient surrogate models of physical applications that circumvent the need for the more expensive simulation techniques entirely and how ML can be used to process large amounts of data.
Journal ArticleDOI
A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
Moloud Abdar,Farhad Pourpanah,Sadiq Hussain,Dana Rezazadegan,Li Liu,Mohammad Ghavamzadeh,Paul Fieguth,Xiaochun Cao,Abbas Khosravi,U. Rajendra Acharya,U. Rajendra Acharya,U. Rajendra Acharya,Vladimir Makarenkov,Saeid Nahavandi +13 more
TL;DR: Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of uncertainties during both optimization and decision making processes as mentioned in this paper, and have been applied to solve a variety of real-world problems in science and engineering Bayesian approximation and ensemble learning techniques are two widely-used types of uncertainty quantification.
Journal ArticleDOI
Morpheus: A Deep Learning Framework For Pixel-Level Analysis of Astronomical Image Data
TL;DR: Morpheus as discussed by the authors leverages advances in deep learning to perform source detection, source segmentation, and morphological classification pixel-by-pixel via a semantic segmentation algorithm adopted from the field of computer vision.
References
More filters
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal Article
Scikit-learn: Machine Learning in Python
Fabian Pedregosa,Gaël Varoquaux,Alexandre Gramfort,Vincent Michel,Bertrand Thirion,Olivier Grisel,Mathieu Blondel,Peter Prettenhofer,Ron Weiss,Vincent Dubourg,Jake Vanderplas,Alexandre Passos,David Cournapeau,Matthieu Brucher,Matthieu Perrot,Edouard Duchesnay +15 more
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Journal ArticleDOI
Deep learning
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Related Papers (5)
LSST: From Science Drivers to Reference Design and Anticipated Data Products
Željko Ivezić,Steven M. Kahn,J. Anthony Tyson,Bob Abel,Emily Acosta,R. A. Allsman,David Alonso,Y. AlSayyad,Scott F. Anderson,John Andrew,James Roger P. Angel,George Z. Angeli,R. Ansari,P. Antilogus,Constanza Araujo,Robert Armstrong,Kirk Arndt,Pierre Astier,Éric Aubourg,Nicole Auza,Tim Axelrod,D. J. Bard,J. Barr,A. Barrau,James G. Bartlett,Amanda E. Bauer,Brian J. Bauman,S. Baumont,Ellen Bechtol,Keith Bechtol,Andrew C. Becker,Jacek Becla,Cristina E. Beldica,Steve Bellavia,Federica B. Bianco,Rahul Biswas,G. Blanc,G. Blanc,Jonathan Blazek,Jonathan Blazek,Roger Blandford,Josh Bloom,J.R. Bogart,Tim W. Bond,Michael T. Booth,A. W. Borgland,Kirk D. Borne,James Bosch,D. Boutigny,Craig A. Brackett,Andrew Bradshaw,W. N. Brandt,Michael E. Brown,James S. Bullock,Patricia R. Burchat,D. L. Burke,Gianpietro Cagnoli,Daniel Calabrese,Shawn Callahan,Alice L. Callen,Jeffrey L. Carlin,Erin L. Carlson,Srinivasan Chandrasekharan,Glenaver Charles-Emerson,Steve Chesley,Elliott Cheu,Hsin Fang Chiang,James Chiang,Carol Chirino,Derek Chow,David R. Ciardi,Charles F. Claver,Johann Cohen-Tanugi,Joseph J. Cockrum,Rebecca Coles,Andrew J. Connolly,Kem H. Cook,Asantha Cooray,Kevin R. Covey,Chris Cribbs,Wei Cui,Roc M. Cutri,P. N. Daly,Scott F. Daniel,Felipe Daruich,Guillaume Daubard,Greg Daues,William A. Dawson,Francisco Delgado,Alfred Dellapenna,Robert de Peyster,Miguel de Val-Borro,Seth Digel,Peter Doherty,Richard Dubois,G. P. Dubois-Felsmann,Josef Durech,Frossie Economou,Tim Eifler,Michael Eracleous,Benjamin L. Emmons,Angelo Fausti Neto,Henry C. Ferguson,Enrique Figueroa,Merlin Fisher-Levine,W. B. Focke,Michael D. Foss,James Frank,Michael D. Freemon,E. Gangler,Eric Gawiser,John C. Geary,Perry M. Gee,Marla Geha,Charles J. B. Gessner,R. R. Gibson,D. Kirk Gilmore,T. Glanzman,William Glick,Tatiana Goldina,Daniel A. Goldstein,Daniel A. Goldstein,Iain Goodenow,Melissa L. Graham,William J. Gressler,Philippe Luc Yves Gris,Leanne P. Guy,Augustin Guyonnet,Gunther Haller,Ron Harris,P. Hascall,Justine Haupt,Fabio Hernandez,Sven Herrmann,Edward Hileman,Joshua Hoblitt,John A. Hodgson,Craig J. Hogan,J. Howard,Dajun Huang,M.E. Huffer,Patrick Ingraham,Walter R. Innes,Suzanne Jacoby,Bhuvnesh Jain,Fabrice Jammes,M. James Jee,M. James Jee,Tim Jenness,G. Jernigan,Darko Jevremović,Kenneth Johns,A. S. Johnson,M. W. G. Johnson,R. Lynne Jones,Claire Juramy-Gilles,Mario Juric,Jason S. Kalirai,Nitya Kallivayalil,Bryce Kalmbach,Jeffrey P. Kantor,P. Karst,Mansi M. Kasliwal,H. Kelly,Richard Kessler,Veronica Kinnison,D. Kirkby,Lloyd Knox,Ivan Kotov,V. Krabbendam,K. Simon Krughoff,Petr Kubánek,John Kuczewski,Shri Kulkarni,John Ku,N. Kurita,Craig S. Lage,Ron Lambert,Travis Lange,J. Brian Langton,Laurent Le Guillou,D. Levine,Ming Liang,Kian Tat Lim,Chris Lintott,Kevin E. Long,Margaux Lopez,Paul J. Lotz,Robert H. Lupton,Nate B. Lust,Lauren A. MacArthur,Ashish Mahabal,Rachel Mandelbaum,Thomas W. Markiewicz,Darren S. Marsh,Philip J. Marshall,S. L. Marshall,Morgan May,Robert McKercher,Michelle McQueen,J. Meyers,Myriam Migliore,M. L. Miller,David Mills,Connor Miraval,Joachim Moeyens,Fred Moolekamp,Fred Moolekamp,David G. Monet,M. Moniez,Serge Monkewitz,Christopher Montgomery,Christopher B. Morrison,Fritz Mueller,Gary P. Muller,Freddy Munoz Arancibia,Douglas R. Neill,Scott P. Newbry,Jean Yves Nief,Andrei Nomerotski,Martin Nordby,Paul O'Connor,John Oliver,Scot S. Olivier,Knut Olsen,William O'Mullane,Sandra Ortiz,Shawn Osier,Russell Owen,Reynald Pain,Paul E. Palecek,John K. Parejko,James B. Parsons,Nathan M. Pease,J. Matt Peterson,John R. Peterson,Don Petravick,M. E.Libby Petrick,C. E. Petry,Francesco Pierfederici,Stephen R. Pietrowicz,R. Pike,Philip A. Pinto,Raymond L. Plante,S. Plate,J. Plutchak,Paul A. Price,Michael Prouza,V. Radeka,J. Rajagopal,Andrew P. Rasmussen,Nicolas Regnault,Kevin Reil,David J Reiss,Michael A. Reuter,Stephen T. Ridgway,Vincent J. Riot,Steve Ritz,Sean Robinson,William Roby,A. Roodman,Wayne Rosing,Cecille Roucelle,Matthew R. Rumore,Stefano Russo,Abhijit Saha,B. Sassolas,T. Schalk,Pim Schellart,Pim Schellart,Rafe Schindler,S. J. Schmidt,Donald P. Schneider,Michael Schneider,William Schoening,German Schumacher,Megan E. Schwamb,Jacques Sebag,Brian M. Selvy,G. H. Sembroski,Lynn G. Seppala,Andrew Serio,Eduardo P. Serrano,Richard A. Shaw,Ian Shipsey,Jonathan Sick,Nicole M. Silvestri,C. T. Slater,J. Allyn Smith,R. Chris Smith,Shahram Sobhani,Christine Soldahl,Lisa J. Storrie-Lombardi,Edward Stover,Michael A. Strauss,Rachel Street,Christopher W. Stubbs,Ian Sullivan,Donald W. Sweeney,John D. Swinbank,John D. Swinbank,Alexander S. Szalay,Péter Takács,Stephen A. Tether,Jon J Thaler,J. G. Thayer,Sandrine Thomas,Adam J. Thornton,V. Thukral,Jeff Tice,David Trilling,M. Turri,Richard Van Berg,Richard Van Berg,Daniel E. Vanden Berk,K. Vetter,Francoise Virieux,Tomislav Vucina,William Wahl,Lucianne M. Walkowicz,Lucianne M. Walkowicz,Brian Walsh,C. W. Walter,Daniel L. Wang,Shin Yawn Wang,Michael Warner,Oliver Wiecha,Beth Willman,Scott Winters,David Wittman,Sidney C. Wolff,W. Michael Wood-Vasey,Xiuqin Wu,Bo Xin,Peter Yoachim,Hu Zhan +335 more