BEGIN:VCALENDAR
PRODID:-//Columba Systems Ltd//NONSGML CPNG/SpringViewer/ICal Output/3.3-
 M3//EN
VERSION:2.0
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTAMP:20260507T094554Z
DTSTART:20260513T120000Z
DTEND:20260513T130000Z
SUMMARY:SQUIDS Seminar (HIMR-funded): Dissecting Deep Neural Networks
UID:{http://www.columbasystems.com/customers/uom/gpp/eventid/}j268-movawk
 zf-gms622
DESCRIPTION:Speaker: Dr Tiffany Vlaar (University of Glasgow)\n\nAbstract
 : \nFirst\, I will discuss the role played by individual layers and subs
 tructures of deep neural networks. Layer-wise sensitivity to the choice 
 of initialisation and optimiser hyperparameter settings varies. I will s
 how that training neural network layers differently can lead to enhanced
  generalisation performance and/or reduced computational cost\, as well 
 as affect resulting adversarial robustness. I will then consider the rol
 e of data and how image annotator variability in real-world ecological d
 atasets affects the performance of deep learning models.\n
STATUS:TENTATIVE
TRANSP:TRANSPARENT
CLASS:PUBLIC
LOCATION:Frank Adams Room 2\, Alan Turing Building\, Manchester
END:VEVENT
END:VCALENDAR