So, are we going to do it?
Can anyone say, to an order of magnitude, how many training positions we need?
Best regards,
Aaron
From: Joaquín Koifman <pamalejo@gmail.com>
Sent: October 19, 2020 11:02 PM
To: Turker Eflanli <turkereflanli@gmail.com>
Cc: Øystein Schønning-Johansen <oysteijo@gmail.com>; Aaron Tikuisis <Aaron.Tikuisis@uottawa.ca>; bug-gnubg@gnu.org <bug-gnubg@gnu.org>
Subject: Re: The status of gnubg?
Attention : courriel externe | external email
I also have many modern computers at disposal if we proceed with the training
I have three computers that can do approximately 250,000 static evaluations / second each: I am happy to help in any way I can
Turker Eflanli
I can comment on that: my experience from 20 years ago was that at some stage adding positions started to hurt the net performance. It is always a balancing act between getting the common/regular positions right and getting the edge cases right.
I think that whatever you do you might want to start fresh and see how my "method" (as you outlined above) can be improved.
Yes, I think I remember that you have mentioned that before. The reasoning behind it might be due to the size (hence capacity) of the neural network. Maybe, with a bigger and deeper neural network, and modern training algorithms, a bigger training set
can be used and still get better performance. As you say, there is a sweet spot between getting the common positions right, and then getting the edge cases right.
Yes, the outlined method is (of course) Joseph's idea. In my view, he is the best backgammon neural network trainer. Maybe I should start this process on my own, and gain some experience before involving a community with effort. It will be really unfortunate
if we waste resources on a braindead idea.
How can the outlined idea be improved? Before I get into that, I think I need some experience, but maybe see if there's some special kind of positions that's over or under represented in the set, and then automagically (in some way) detect these?
-Øystein
|