BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:STANDARD
TZNAME:GMT
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:BST
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:6a3d6e9addf27
DTSTAMP:20260625T180826Z
DTSTART;TZID=Europe/London:20201007T141500
DTEND;TZID=Europe/London:20201007T151500
TZID:Europe/London
SUMMARY:Statistics Seminar: Christopher Yau (University of Manchester)
DESCRIPTION:Title: Variations of Variational Autoencoders.Abstract: Variational Autoencoders (VAE) have become a popularapproach for implementing Bayesian latent variable models forapplications involving high-dimensional and/or large sample size datasets in recent years. By leveraging the use of modern programmingframeworks for constructing models based on deep neural networks, VAEshave been extensively used for unsupervised dimensionality reductionparticularly in image analysis. In this talk, I will describe somenovel variants of VAEs that we have developed to improve theirapplicability for problems in computational biology involving 'omicsdatasets. https://events.st-andrews.ac.uk/events/statistics-seminar-christopher-yau-university-of-manchester/
URL:https://events.st-andrews.ac.uk/events/statistics-seminar-christopher-yau-university-of-manchester/
End:VEVENT
End:VCALENDAR