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]> wrote:

> On Mon, Oct 19, 2020 at 7:52 PM Joseph Heled <[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