BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Canada/Eastern
BEGIN:DAYLIGHT
DTSTART:20220313T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20211107T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220328T183401Z
UID:F7D51737-9280-4DEF-92EE-9481C9F14865
DTSTART;TZID=Canada/Eastern:20211207T170000
DTEND;TZID=Canada/Eastern:20211207T183000
DESCRIPTION:Prerequisites: You do not need to have attended the earlier tal
 ks. If you know zero math and zero machine learning\, then this talk is fo
 r you. Jeff will do his best to explain fairly hard mathematics to you. If
  you know a bunch of math and/or a bunch machine learning\, then these tal
 ks are for you. Jeff tries to spin the ideas in new ways.\n\nLonger Abstra
 ct: Suppose you have a distributions of random images of cats. Suppose you
  want to learn a neural network that takes uniformly random bits as input 
 and outputs an image of a cat according to this same distribution. One fun
  thing is that this neural network won't be perfect and hence it will outp
 ut images of "cats" that it has never seen before. Also you can make small
  changes in the network input bits and see how it changes the resulting im
 age of a cat. The way we do this is with Generative Adversarial Networks. 
 This is formed by having two competing agents. The task of the first agent
 \, as described above\, is to output random images of cats. The task of th
 e second is to discern whether a given image was produced by the true rand
 om distribution or by the first agent. By competing\, they learn. If we ha
 ve more time in the talk then we will talk about Convolutional & Recurrent
  Networks which are used for learning images and sound that are invariant 
 over location and time.\n\nVirtual: https://events.vtools.ieee.org/m/28924
 1
LOCATION:Virtual: https://events.vtools.ieee.org/m/289241
ORGANIZER:ayda.naserialiabadi@ryerson.ca
SEQUENCE:1
SUMMARY:Generative Adversarial Networks: Used for understanding and produci
 ng a random data item
URL;VALUE=URI:https://events.vtools.ieee.org/m/289241
X-ALT-DESC:Description: <br /><p><strong>&nbsp\;Prerequisites: </strong>You
  do not need to have attended the earlier talks. If you know zero math and
  zero machine learning\, then this talk is for you. Jeff will do his best 
 to explain fairly hard mathematics to you. If you know a bunch of math and
 /or a bunch machine learning\, then these talks are for you. Jeff tries to
  spin the ideas in new ways.</p>\n<p><strong>Longer Abstract:&nbsp\;</stro
 ng>Suppose you have a distributions of random images of cats. Suppose you 
 want to learn a neural network that takes uniformly random bits as input a
 nd outputs an image of a cat according to this same distribution. One fun 
 thing is that this neural network won't be perfect and hence it will outpu
 t images of "cats" that it has never seen before. Also you can make small 
 changes in the network input bits and see how it changes the resulting ima
 ge of a cat. The way we do this is with Generative Adversarial Networks. T
 his is formed by having two competing agents. The task of the first agent\
 , as described above\, is to output random images of cats. The task of the
  second is to discern whether a given image was produced by the true rando
 m distribution or by the first agent. By competing\, they learn. If we hav
 e more time in the talk then we will talk about Convolutional &amp\; Recur
 rent Networks which are used for learning images and sound that are invari
 ant over location and time.</p>
END:VEVENT
END:VCALENDAR