What is Watson?

[Terry McCracken]

This is Watson

[kgburcham]

this is watson against champs

http://www.youtube.com/watch?v=WFR3lOm_xhE&feature=fvst

[Leto]

This one has the entire episodes:
day 1 part 1: http://www.youtube.com/watch?v=ZLdkJpAtt1I
day 1 part 2: http://www.youtube.com/watch?v=FXH7jn2A ... ion_339967

day 2 part 1: http://www.youtube.com/watch?v=PHhDLUVAtqU
day 2 part 2: http://www.youtube.com/watch?v=HR2_M8kL ... ion_734551

day 3 part 1: http://www.youtube.com/watch?v=l2_fM6e9 ... ion_911611
day 3 part 2: http://www.youtube.com/watch?v=DHGu0-p- ... tion_10124

Great achievement and a good first step towards creating Star Trek's Data.

[Frank Quisinsky]

The programming partner from Microsoft and Sherlock Holmes I think, or not?

Cloned in much chess programs, because the error messages are often the same

Best
Frank

[NATIONAL12]

wonder what brought this subject up.

[Vinvin]

Many thanks, Leto !!

[jplchess]

To the computer chess community:

http://www.youtube.com/watch?v=d_yXV22O6n4&NR=1

This computer learns and knows puns.

CCC has someone talking about IBM Watson almost 2 years ago.

In more related news, does computer chess software learn from a mistake that has a relatively decent time control and number of plies?

Jonathan Lee

[Dann Corbit]

To the computer chess community:

http://www.youtube.com/watch?v=d_yXV22O6n4&NR=1

This computer learns and knows puns.

CCC has someone talking about IBM Watson almost 2 years ago.

In more related news, does computer chess software learn from a mistake that has a relatively decent time control and number of plies?

Jonathan Lee

Some programs have position learning.
Some programs have evaluation learning.
Some programs have book learning.

[Terry McCracken]

To the computer chess community:

http://www.youtube.com/watch?v=d_yXV22O6n4&NR=1

This computer learns and knows puns.

CCC has someone talking about IBM Watson almost 2 years ago.

In more related news, does computer chess software learn from a mistake that has a relatively decent time control and number of plies?

Jonathan Lee

Some programs have position learning.
Some programs have evaluation learning.
Some programs have book learning.

Do any have all three and are they any good?

[Dann Corbit]

To the computer chess community:

http://www.youtube.com/watch?v=d_yXV22O6n4&NR=1

This computer learns and knows puns.

CCC has someone talking about IBM Watson almost 2 years ago.

In more related news, does computer chess software learn from a mistake that has a relatively decent time control and number of plies?

Jonathan Lee

Some programs have position learning.
Some programs have evaluation learning.
Some programs have book learning.

Do any have all three and are they any good?

Some have all three.

Evaluation learning via td-lamda and td-leaf are the least effective, from what I have seen (custom evaluation seems to do better).

Position learning is 100% effective if you hit the same position again (but this has a surprisingly low probability). Suppose (for instance) that you are playing a chess game and encounter this position:
[d]2r3k1/4ppb1/2P5/4P2p/2R3p1/1p6/1B4PP/5K2 w - -
Your chess engine makes a bad move and writes out a record that stores the correct value after the opponent's move. The odds that you are going to play this move again are basically zero, unless it is near the origin (in which case it is probably a book move).

Book learning is effective, but it gets poisoned if you run lots of blitz games. IOW, if you run nothing but correspondence time control with an ultra strong program, eventually you will get a nearly perfect book. However, it will take a very long time to get there.

The problem with blitz book learning is that a computer program can easily make a mistake because of a shallow search. The book gets updated with this new wrong answer. So the engine will avoid moves that have this move now flagged as bad, but potentially it is a good move.

My synopsis:
The only one of these strategies that actually work well in practice is book learning and the only way that book learning will work optimally is if you run at very, very slow time control and with a very strong engine.

Eventually, computers will become fast enough that blitz time control will safely update book learning, but I guess that this is still some years away.

I think that there is a long way to go before computers utilize chess statistics properly in learning and move selection. It is actually something that I am actively working on.