AlphaGo Zero: Discovering new knowledge

Subscribers:
663,000
Published on ● Video Link: https://www.youtube.com/watch?v=WXHFqTvfFSw



Category:
Let's Play
Duration: 2:41
116,403 views
0


DeepMind's Professor David Silver describes AlphaGo Zero, the latest evolution of AlphaGo, the first computer program to defeat a world champion at the ancient Chinese game of Go. Zero is even more powerful and is arguably the strongest Go player in history.

Previous versions of AlphaGo initially trained on thousands of human amateur and professional games to learn how to play Go. AlphaGo Zero skips this step and learns to play simply by playing games against itself, starting from completely random play. In doing so, it quickly surpassed human level of play and defeated the previously published champion-defeating version of AlphaGo by 100 games to 0.

If similar techniques can be applied to other structured problems, such as protein folding, reducing energy consumption or searching for revolutionary new materials, the resulting breakthroughs have the potential to positively impact society.

Find out more here: https://deepmind.com/blog/alphago-zero-learning-scratch




Other Videos By Google DeepMind


2018-05-09Grid cells - Caswell Barry, UCL
2018-03-29Retour de Rémi Munos en France et ouverture de DeepMind Paris
2018-03-07A systems neuroscience approach to building AGI - Demis Hassabis, Singularity Summit 2010
2018-03-07Measuring machine intelligence - Shane Legg, Singularity Summit 2010
2018-03-06Defining principles for tech companies in the NHS: DeepMind Health's Collaborative Listening Summit
2018-01-29Designing Streams with clinicians (with subtitles)
2017-11-07DeepMind Health – how our Streams app is used at the Royal Free (with subtitles)
2017-10-24DeepMind Health - What Patients Want From Tech: Patient Engagement Events 2017
2017-10-24DeepMind Health - What Patients Want From Tech: Patient Engagement Events 2017 (with subtitles)
2017-10-18AlphaGo Zero: Starting from scratch
2017-10-18AlphaGo Zero: Discovering new knowledge
2017-09-15Ke Jie and DeepMind's Go Ambassador Fan Hui review the 2nd AlphaGo vs Ke Jie game
2017-09-15Ke Jie and DeepMind's Go Ambassador Fan Hui review the 1st AlphaGo vs Ke Jie game
2017-09-15Ke Jie and DeepMind's Go Ambassador Fan Hui review the 3rd AlphaGo vs Ke Jie game
2017-09-06ICML 2017: Test of Time Award (Sylvain Gelly & David Silver)
2017-08-10DeepMind open source PySC2 toolset for Starcraft II
2017-08-10Trained and untrained agents play StarCraft II full 1vs1 game
2017-08-10StarCraft II 'mini games' for AI research
2017-07-24NIPS 2015 Symposium: Brains, Minds and Machines (Demis Hassabis)
2017-07-14Emergence of Locomotion Behaviours in Rich Environments
2017-06-19The Future of Go Summit: AlphaGo & Ke Jie match 3 moves analysis