Yes, good questions. I think the first task is to work up to & establish a benchmark with a 20x256 NN, because right now we don't really know what that benchmark (true chess strength) is.mirek wrote:... I wonder by how much can the NN be increased before the the decrease in nps will cause overall negative elo gain. Even if one could run every NN in constant time (independent of NN size) there is probably diminishing elo gain by doubling the NN size, so there will be some finite limit even for infinite sum of NN doublings.
I am also wondering if there are any other NN architectures that are being considered that could go beyond what just scaling of current architecture can achieve.
2 open projects
Moderators: hgm, Rebel, chrisw
-
- Posts: 1470
- Joined: Mon Apr 23, 2018 7:54 am
Re: 2 open projects
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: 2 open projects
Are you referring to the paper, or is there a talk you can link to?MonteCarlo wrote: Silver said in that keynote talk that they did multiple runs, and I'm pretty sure they didn't publish the results of a run where they had the sorts of bugs the Leela project has had so far
There's very little point idly speculating about what can and can't be achieved by the project.
Time will tell.
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."
-
- Posts: 5566
- Joined: Tue Feb 28, 2012 11:56 pm
Re: 2 open projects
Probably this:Albert Silver wrote:Are you referring to the paper, or is there a talk you can link to?MonteCarlo wrote: Silver said in that keynote talk that they did multiple runs, and I'm pretty sure they didn't publish the results of a run where they had the sorts of bugs the Leela project has had so far
There's very little point idly speculating about what can and can't be achieved by the project.
Time will tell.
https://www.youtube.com/watch?v=Wujy7OzvdJk
-
- Posts: 3019
- Joined: Wed Mar 08, 2006 9:57 pm
- Location: Rio de Janeiro, Brazil
Re: 2 open projects
Thanks!syzygy wrote:Probably this:Albert Silver wrote:Are you referring to the paper, or is there a talk you can link to?MonteCarlo wrote: Silver said in that keynote talk that they did multiple runs, and I'm pretty sure they didn't publish the results of a run where they had the sorts of bugs the Leela project has had so far
There's very little point idly speculating about what can and can't be achieved by the project.
Time will tell.
https://www.youtube.com/watch?v=Wujy7OzvdJk
"Tactics are the bricks and sticks that make up a game, but positional play is the architectural blueprint."