News for hackers. Stuff that matters.
Re:AlphaGo Is Not AI by pps43 on Sunday March 19, 2017 @10:46PM (#13911335)
I'm not sure about human players, but it might be possible to build an adversarial neural network that beats AlphaGo (and only AlphaGo).
Re:AlphaGo Is Not AI by Dzugaru on Monday March 20, 2017 @04:59AM (#13912675)
I thought AlphaGo is trained in an adversarial manner already (it plays against itself).
Re:AlphaGo Is Not AI by pps43 on Monday March 20, 2017 @01:16PM (#13915884)
The version that played against Fan Hui was reportedly trained that way, but if I recall correctly the more recent one that played Lee Sedol did't rely on self-play as much.

Also the objective was different - they tried to train a network that would play well against any opponent. It should be easier to train a network that exploits some very narrow weakness in specific AlphaGo version.

For example, my phone consistently beats me at chess. But I found a sequence of moves in one opening where is always makes the same mistake, and I after that I can win easily.