Semi-skeptical discussion of the Google Go-playing paper: https://medium.com/backchannel/has-deepmind-really-passed-go-adc85e256bec#.lar62he8k … (HT @concutere & others)
-
-
The deep-learning image recognition results are genuinely interesting—unlike the Go ones—because recognition is a real, and nebulous, task.
-
Boardgame programs all have two parts: tree search to look ahead at future moves, and a static evaluator that says how good the board looks
- 28 more replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.