BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Anjitha Jon Williams (CFT)\, Photometric redshifts for Kilo-Degree
  Survey quasars with deep learning
DTSTART;VALUE=DATE-TIME:20241024T083000Z
DTEND;VALUE=DATE-TIME:20241024T084500Z
DTSTAMP;VALUE=DATE-TIME:20260518T125830Z
UID:indico-contribution-1739@events.ncbj.gov.pl
DESCRIPTION:Redshift is the key quantity in cosmology. In modern wide-angl
 e deep surveys\, most of the redshifts are derived indirectly from photome
 try rather than spectroscopy. In this talk\, I will discuss the use of Con
 volutional Neural Networks (CNN) for photometric redshift (photo-z) estima
 tion of Quasars of the Kilo-Degree Survey (KiDS) DR4. CNNs have recently s
 hown promise in accurately estimating photometric redshifts\, leveraging t
 he ability of deep learning algorithms to capture complex patterns in larg
 e datasets. I propose a new architecture based on CNN to estimate the phot
 ometric redshift of Quasars by training the network with images supplement
 ed with magnitudes. In this talk\, I will describe the architecture of our
  deep learning model and the training process\, the effect of model hyperp
 arameters and data preprocessing on photo-z estimation and\, highlight the
  advantages of using a CNN over traditional machine learning algorithms. I
  will present the results of experiments\, comparing the performance of th
 e model to other state-of-the-art photometric redshift estimation methods.
 \n\nhttps://events.ncbj.gov.pl/event/364/contributions/1739/
LOCATION:
URL:https://events.ncbj.gov.pl/event/364/contributions/1739/
END:VEVENT
END:VCALENDAR