BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260917T140600Z
UID:Seminar-ACTO/Networks-1053@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Othon Michail:MAILTO:Othon.Michail@liverpool.ac.uk
DTSTART:20230523T140000
DTEND:20230523T150000
SUMMARY:ACTO/Networks Series
DESCRIPTION:Konstantinos Tsakalidis: Deep neural network training acceleration with geometric data structures\n\nThe efficiency of deep learning applications deteriorates significantly as the sizes of the training data and of the neural networks grow larger. In this talk we will identify beyond-state-of-the-art open problems in the intersection of deep learning with computational geometry. Motivated by the recent application of dynamic data structures for geometric halfspace range searching in the acceleration of deep neural networks' training and preprocessing complexity, we revisit efficient algorithms for constructing geometric multi-dimensional data structures and maintaining them dynamically.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=1053
LOCATION:Ashton Lecture Theatre
END:VEVENT
END:VCALENDAR