Deep learning for supernovae detection

Simple item page
dc.contributor.advisorBassett, Bruceen_ZA
dc.contributor.authorAmar, Giladen_ZA
dc.date.accessioned2018-01-30T10:23:06Z
dc.date.available2018-01-30T10:23:06Z
dc.date.issued2017en_ZA
dc.description.abstractIn future astronomical sky surveys it will be humanly impossible to classify the tens of thousands of candidate transients detected per night. This thesis explores the potential of using state-of-the-art machine learning algorithms to handle this burden more accurately and quickly than trained astronomers. To this end Deep Learning methods are applied to classify transients using real-world data from the Sloan Digital Sky Survey. Using cutting-edge training techniques several Convolutional Neural networks are trained and hyper-parameters tuned to outperform previous approaches and find that human labelling errors are the primary obstacle to further improvement. The tuning and optimisation of the deep models took in excess of 700 hours on a 4-Titan X GPU cluster.en_ZA
dc.identifier.apacitationAmar, G. (2017). <i>Deep learning for supernovae detection</i>. (Thesis). University of Cape Town ,Faculty of Science ,Cosmology and Gravity Group. Retrieved from http://hdl.handle.net/11427/27090en_ZA
dc.identifier.chicagocitationAmar, Gilad. <i>"Deep learning for supernovae detection."</i> Thesis., University of Cape Town ,Faculty of Science ,Cosmology and Gravity Group, 2017. http://hdl.handle.net/11427/27090en_ZA
dc.identifier.citationAmar, G. 2017. Deep learning for supernovae detection. University of Cape Town.en_ZA
dc.identifier.ris TY - Thesis / Dissertation AU - Amar, Gilad AB - In future astronomical sky surveys it will be humanly impossible to classify the tens of thousands of candidate transients detected per night. This thesis explores the potential of using state-of-the-art machine learning algorithms to handle this burden more accurately and quickly than trained astronomers. To this end Deep Learning methods are applied to classify transients using real-world data from the Sloan Digital Sky Survey. Using cutting-edge training techniques several Convolutional Neural networks are trained and hyper-parameters tuned to outperform previous approaches and find that human labelling errors are the primary obstacle to further improvement. The tuning and optimisation of the deep models took in excess of 700 hours on a 4-Titan X GPU cluster. DA - 2017 DB - OpenUCT DP - University of Cape Town LK - https://open.uct.ac.za PB - University of Cape Town PY - 2017 T1 - Deep learning for supernovae detection TI - Deep learning for supernovae detection UR - http://hdl.handle.net/11427/27090 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/27090
dc.identifier.vancouvercitationAmar G. Deep learning for supernovae detection. [Thesis]. University of Cape Town ,Faculty of Science ,Cosmology and Gravity Group, 2017 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/27090en_ZA
dc.language.isoengen_ZA
dc.publisher.departmentCosmology and Gravity Groupen_ZA
dc.publisher.facultyFaculty of Scienceen_ZA
dc.publisher.institutionUniversity of Cape Town
dc.subject.otherApplied Mathematicsen_ZA
dc.subject.otherAstronomyen_ZA
dc.titleDeep learning for supernovae detectionen_ZA
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationnameMScen_ZA
uct.type.filetypeText
uct.type.filetypeImage
uct.type.publicationResearchen_ZA
uct.type.resourceThesisen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_sci_2017_amar_gilad.pdf
Size:
11.38 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Masters