BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ZContent.net//ZapCalLib 1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTART;TZID=Atlantic/Canary:20240123T123000
DTEND;TZID=Atlantic/Canary:20240123T133000
UID:iactalks-1737
X-WR-CALNAME: IAC Talks: Open Astronomy Seminars
X-ORIGINAL-URL: /iactalks/Talks/view/1737
CREATED:2024-01-23T12:30:00+00:00
X-WR-CALDESC: IAC Talks upcomming talks
SUMMARY:Revealing Galaxy Morphology with Spectral Data and Unsupervised Tec
 hniques
DESCRIPTION:Revealing Galaxy Morphology with Spectral Data and Unsupervised
  Techniques\nDr. José Antonio de Diego Onsurbe\n\nUsing unsupervised mach
 ine learning methods, we present a novel approach to classifying galaxies 
 into early and late types based on their spectral characteristics. The res
 earch utilizes a balanced dataset of 2000 galaxies from the Galaxy Zoo 2 a
 nd spectral data from the Sloan Digital Sky Survey Data Release 13. The me
 thodology involves applying an Autoencoder Neural Network for dimensionali
 ty reduction, followed by a Gaussian Mixture Model for clustering. The stu
 dy demonstrates that this approach achieves an accuracy rate of approximat
 ely 86% in galaxy classification, highlighting the potential of unsupervis
 ed machine learning techniques in enhancing the precision and efficiency o
 f morphological classification of galaxies based on spectral data.\n 
END:VEVENT
END:VCALENDAR