DeepBlue
12/24/2017
/
By Zoey Sky
New level of intelligence: A new AI can teach itself with a “reinforcement learning algorithm” resulting in “superhuman” abilities within hours
It has been two decades since DeepBlue defeated Garry Kasparov in a match, but chess players were surprised by another development. The AlphaZero algorithm, a collaboration between Google and DeepMind, has recently shattered records. Even though DeepMind’s AlphaZero played against itself for only four hours, it managed to “synthesize the chess knowledge of one and a half millennium.” […]
« Return Home
1 of 1
Popular Articles
COPYRIGHT © 2017 INVENTIONS NEWS
Privacy Policy