AlphaGo beats Ke Jie again to wrap up three-part match

Re:AlphaGo beats Ke Jie again to wrap up three-part match by hajile on Thursday May 25, 2017 @11:38AM (#14417960)

Go works precisely because it is a small closed system. An interesting match (from an AI perspective) would be a pro playing alphago on an unusual board (eg, one in the shape of a cat). The pro would take everything he knows about the game and apply it to the odd situation. Alphago is so specifically tuned that it cannot even handle any case except 19x19 (and maybe 9x9). Another interesting question would be small rules changes like "you may not play on any star points or any point directly touching them until turn 30".

Go has deep strategy, but it is very well defined in terms of what can and cannot be done and those rules are not particularly complex. Power grids in contrast are far more complex. There are thousands of rules, but also many more thousands of unwritten assumptions and case-by-case analysis. A final issue is that there exist unsolved and unrecognized problems.

The last AI winter (deep learning is just the latest rebrand) came from researchers overstating their accomplishments and making promises about general intelligence that could not be kept. Any claim about anything that requires general intelligence in the near future is undoubtedly overpromising.

[ Parent | on HN ]

Re:AlphaGo beats Ke Jie again to wrap up three-part match by sangnoir on Thursday May 25, 2017 @04:22PM (#14419857)

> Alphago is so specifically tuned that it cannot even handle any case except 19x19 (and maybe 9x9).

Do you have any sources to back this assertion? It sounds unintuitive as I know object recognition sytema are usually trained on small images but they generalize well to arbitrary image sizes. What you are describing sounds like overfitting.

[ Parent | on HN ]

Re:AlphaGo beats Ke Jie again to wrap up three-part match by hajile on Thursday May 25, 2017 @11:09PM (#14421747)

The paper itself repeatedly says that all 48 layers of the policy network are 19x19 matrices. To make the point though, they initially train alphago using actual games. After a hundred thousand or so training games, it's finally ready to start playing and learning. There are less than a couple dozen recorded games on larger boards.

If you haven't played go very much, you may thing that "it's just a bigger board". 19x19 is commonly used because it has an even balance of edge and center influence (in reality, edge influence seems to be slightly higher). With the 13x13, corner plays have overwhelming influence in the center. At 9x9, there is basically no center strategy at all. Normal strategies starting in the corners and expanding influence toward the center don't work as effectively with larger boards (the larger the board, the more this becomes true).

This is a much different issue than image recognition in that strategy doesn't scale in the same way that images do.

[ Parent | on HN ]