BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Learning for Vision: Lecture and Workshop - Alberto Rizzoli\,
  Andrea Azzini\, Simon Edwardsson\; v7labs
DTSTART:20200226T190000Z
DTEND:20200226T203000Z
UID:TALK140392@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:In this interactive workshop\, we will collaboratively build a
  robust object segmentation AI\, trained a common item\, and later identif
 y its flaws and limitations. Participants will be given access to an inter
 active dataset platform where they can view\, label\, and capture addition
 al image data to train a neural network. We will train a model during the 
 lecture\, and run it in real-time to identify its strengths and weaknesses
  and how this may affect real-world applications.\n\nDeep learning allows 
 computer vision systems to skyrocket form a number of hand-crafted heurist
 ics in traditional vision engineering\, to millions of automatically learn
 ed parameters\, allowing it to learn almost anything. Backed by significan
 t hype\, it seems to break through all the challenges presented by AI\, bu
 t where does it still fail\, and why?\n\nTopics covered include: A brief h
 istory of computer vision\, what data can and cannot be learned\, strength
 s and limitations of supervised learning\, training a Mask-RCNN model via 
 Pytorch\, monitoring an AI's performance.\n\nFree pizza and beer available
  after the talk!
LOCATION:Wolfson Hall\, Churchill College
END:VEVENT
END:VCALENDAR