Complete gig history
All talks by Brian Christian
6 talks·6 with video·6 years
Loading talks…
בשנת 2013, קבוצת חוקרים רצתה ליצור בינה מלאכותית שתוכל לנצח בכל המשחקים של חברת אטארי. הם פיתחו מערכת בשם Deep Q Networks ...
Nous avons un défi en commun avec les ordinateurs: comment faire le plus de choses possible en un temps limité. Depuis une ...
In 2013, a group of researchers wanted to create an AI system that could beat every Atari game. They developed a system called Deep Q Networks (DQN) and less than two years later, it was superhuman. But there was one notable exception. When playing Montezuma's Revenge, DQN couldn't score a single point. What was it that made this game so vexingly difficult for AI? Brian Christian investigates. [Directed by Gavin Edwards, Movult, narrated by Jack Cutmore-Scott, music by Salil Bhayani, cAMP Studio].
Human beings and computers alike share the challenge of how to get as much done as possible in a limited time. Over the last fifty or so years, computer scientists have learned a lot of good strategies for managing time effectively— and they have a lot of experience with what can go wrong. Brian Christian shares how we can use some of these insights to help make the most of our own lives. [Directed by Draško Ivezić, narrated by Addison Anderson].
Subscribe to O'Reilly on YouTube: http://goo.gl/n3QSYi Follow O'Reilly on Twitter: http://twitter.com/oreillymedia Facebook: ...
Our 2012 theme was "Identity" This year we explored Identity in a way that went beyond the standard gender/race/age lines.