TalkChess.com

All of the architectures currently in common use in computer chess are derived from Deepmind’s Alpha Zero work. Stacked ResNets are common in image recognition. I assure you you'll find none of Alpha-Zero specific changes to *that* in Stoofvlees. The Alpha Zero changes are really how to map the res...

NN-based engine consists of 3 parts: 1. Neural network. 2. Engine. 3. Training script. You need 2 of 3 to be unique to be unique. It’s so detached from reality! What is “training script” doing here? I was really perplexed. Who came up with those “2 of 3”? Training script is something that can be wr...

I’m not sure if you realize this, but lczero and lc0 are two distinct engines. The first, lczero, was the initial chess engine used by the leela chess project and was derived from a combination of the leela go engine and stockfish chess board logic. The second, lc0, was a rewrite from scratch. I’m ...

You can try this with Stoofvlees as well (you should have a copy). I expect it to do even better than lc0.

I am never going to spend hundreds of euros for a graphic card and cooling and electricity bills just to be able to run NN engines. It seems rather likely that increasing NN support in new CPU architectures and improvements in NN engines will make the issue moot. lc0-CPU-LD2 is a reasonably strong ...

Paloma wrote: ↑

Wed Aug 28, 2019 8:55 pm

So only Houdini, Komodo, Fire, Ethereal and Xiphos are without neural networks.
Pure A/B Engines seem to be out.

Fire has a NN version, it played in TCEC.

Zenmastur wrote: ↑

Tue Jul 30, 2019 8:05 am

more about where the people spending the ICGA's money want to vacation this year!

It seems to be where the IJCAI (to which the ICGA linked itself?) is holding its conferences, more than anything the ICGA itself wants.

Note that Stoofvlees doesn't support pondering (yet), so I would expect it to be weak in pb=on rating lists.

Yes, otherwise I don't understand the scores. Do they say if they allowed the Boost? i9 9900k on 1-2 cores can go to 5.0GHz, while Ryzen 3900X 1 core to 4.6GHz. If they allowed the boost, many single-thread benchmarks will look bad for Ryzen in this comparison. Leela is a curiosity in this benchmar...

I'm already talking about the revised numbers. The original ones (now deleted) showed that the 3700X was the same speed as the 2700X, which obviously couldn't be true.

In the new data it clearly gains, but not enough to catch Intel.