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 <[email protected]>
Sent: October 19, 2020 11:02 PM
To: Turker Eflanli <[email protected]>
Cc: Øystein Schønning-Johansen <[email protected]>; Aaron Tikuisis 
<[email protected]>; [email protected] <[email protected]>
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

El lun., 19 oct. 2020 a las 16:33, Turker Eflanli 
(<[email protected]<mailto:[email protected]>>) escribió:
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

On Mon, Oct 19, 2020 at 2:29 PM Øystein Schønning-Johansen 
<[email protected]<mailto:[email protected]>> wrote:
On Mon, Oct 19, 2020 at 7:52 PM Joseph Heled 
<[email protected]<mailto:[email protected]>> wrote:
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

Reply via email to