New level of intelligence: A new AI can teach itself with a “reinforcement learning algorithm” resulting in “superhuman” abilities within hours

(Natural News) 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…

Read Original Article: New level of intelligence: A new AI can teach itself with a “reinforcement learning algorithm” resulting in “superhuman” abilities within hours »

Powered by WPeMatico