BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Decision-making and artificial general intelligence using deep neu
 ral networks - Audrunas Gruslys\, Google Deep Mind
DTSTART:20170207T160000Z
DTEND:20170207T170000Z
UID:TALK70241@talks.cam.ac.uk
CONTACT:CCA
DESCRIPTION:Deep neural networks have been remarkably successful models th
 at have led to breakthroughs in a wide variety tasks\, including classific
 ation\, density estimation and reinforcement learning. Various reinforceme
 nt learning algorithms have used deep neural networks to master a variety 
 of computer games\, ranging from simple Atari games to complex 3D navigati
 on tasks. Progress in deep learning has been driven by improved neural net
 work architectures and training methods using insights from linear algebra
 \, probability theory\, statistics\, and optimization theory. For example\
 , the combination of Monte Carlo tree search and deep learning allowed Alp
 haGo to master the game of Go. In this talk I will give a broad overview o
 f our research at DeepMind\, including both the areas of deep and reinforc
 ement learning. 
LOCATION:MR14
END:VEVENT
END:VCALENDAR