TalkChess.com

Part 2. Are the inputs to your neural network unique? Answer. Only if you are Scorpio. You forgot Stoofvlees. As the person who trained Maddex (that’s the net Scorpio is running), I know exactly what the inputs to it were. You can read up on it here: https://github.com/dkappe/leela-chess-weights/wi...

Basically, right now, if you are piggybacking on LCZero engine, your entity is to all intents and purposes a 100% clone. Trying to persuade TCEC is another thing in itself. They’ve built on the idea there is some kind if competition going on with different entities in it, especially with these “exc...

I recently tested Allie vs Lc0 on similarity, same NN's thus testing the code base. http://rebel13.nl/html/nn-500ms.html http://rebel13.nl/html/nn-1000ms.html 75% is pretty high. But then NN is a whole different subject in comparison when it's about similarity. I’m sorry, you tested these engines w...

I recently tested Allie vs Lc0 on similarity, same NN's thus testing the code base. http://rebel13.nl/html/nn-500ms.html http://rebel13.nl/html/nn-1000ms.html 75% is pretty high. But then NN is a whole different subject in comparison when it's about similarity. I’m sorry, you tested these engines w...

At some point a NN engine will beat lc0 in TCEC, and like the swallows returning to Capistrano, you will pen another missive about how they need to be banned. I look forward to your ongoing contortions.

The initial Bad Gyal, some 2M+ games, has finished uploading.

https://github.com/dkappe/leela-chess-w ... -Gyal-Data

Eduard wrote: ↑

Mon Sep 09, 2019 12:08 pm

I have tested many different small networks in analysis mode, and the LD2 is the best.

Certainly true on GPU, and at higher time controls on CPU, but you have to have a little bit of patience using LD2 on CPU.

OK, I'll rephrase the question. What is the best network and settings for any NN on 7 threads of an 8 core, very fast i7 machine? LD2 is beating 11248 on that config by 345 elo in my current test, so the question is whether some other network is even better, and whether default settings are appropr...

mesilikas wrote: ↑

Fri Sep 06, 2019 9:35 pm

Can you recommend some settings dkappe?

Default should be good for starters (though a higher number of threads are useful on more powerful CPU's).

Which NN network, Lc0 or other, is currently believed to be the strongest one for use only on a CPU, no GPU? I've seen posts on this before, but this is always changing. I understand it should be a small network. No doubt, that LD2 is the strongest for CPU. 10x128 built out of T40 training games. h...