BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20260912T154022Z
UID:Seminar-dept-399@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20160202T130000
DTEND:20160202T140000
SUMMARY:School Seminar Series
DESCRIPTION:Dr. Ben Graham: Spatially Sparse Convolutional Neural networks\n\nConvolutional neural networks (CNNs) perform well on 2D and 3D classification problems such as handwriting recognition, image classification, and 3D object recognition.\n\nIf the input to a convolutional network is sparse, for example a 1D pen stroke on a 2D piece of paper, of a 2D surface in 3D space, then it makes sense to use that sparsity to reduce computational cost.\n\nThis is just like matrix arithmetic: if you are dealing with sparse matrices, you can save memory and time by using an appropriate data structure.\n\nWhat is interesting is that this allows us to look at sparse spatial structures at higher resolution than would otherwise be practical.\n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=399
LOCATION:Ashton Lecture Theater
END:VEVENT
END:VCALENDAR