News for hackers. Stuff that matters.
Re:Yann LeCun's comment on AlphaGo and true AI by bbsome on Monday March 14, 2016 @05:16AM (#11281765)
Note, that these features are for the RollOut fast policy. The reason is that this needs to be fast, so rather than a net they have a linear policy. A linear policy in order to work it requires good feature selection, which is what this is. In some future, when we have better hardware, you can imagine removing the roll out policy and having just one.
Re:Yann LeCun's comment on AlphaGo and true AI by aprescott on Monday March 14, 2016 @09:37AM (#11282781)
I think you're confusing this list of attributes with a separate list used for rollouts and tree search. The ones above are definitely used for the neutral networks in the policy and value networks. See: "Extended Data Table 2: Input features for neural networks. Feature planes used by the policy network (all but last feature) and value network (all features)."