BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:An exposition of memory-augmented artificial neural networks
DTSTART:20170303T110000
DTEND:20170303T120000
DTSTAMP:20260528T020250Z
UID:f05e3bd8c29a6cebe3188112a5b749c628d7f5cf35c7ac4b67b6ff35
CATEGORIES:Conferences - Seminars
DESCRIPTION:William Mycroft (Sheffield)\nBiologically inspired machine lea
 rning algorithms known as artificial neural networks have been around sinc
 e the 1950s\, but have rapidly gained popularity over the last decade due 
 to increases in computational power and the sheer volume of data available
 . The simplest forms of these\, feed-forward neural networks\, have two ma
 jor shortcomings: they require input of fixed length and handle each input
  independently. As such these algorithms have no "memory" and are unsuitab
 le for sequence learning problems. Simple variants\, recurrent neural netw
 orks\, equip the neural network with a basic internal memory and have show
 n success in handling such problems. However\, this memory is inherently s
 hort-lived and these networks struggle to learn longer term dependencies. 
 A very recent biologically inspired variant\, neural Turing machines\, aug
 ment the network with an external memory and show potential to address suc
 h problems.
LOCATION:Campus Biotech\, B1.06 (lakeside)
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR