Search found 1134 matches

by Gian-Carlo Pascutto
Thu Sep 19, 2019 7:11 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

So for the record, you agree that the lc0 cuDNN/CUDA backend is a very critical part to the strength of an NN-engine? I think I've been very clear and said *numerous times* that the cudann backend is a very important critical piece of code...But to be very clear, the sentiment I was relating above ...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 6:20 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

The pieces were all there, Deep Mind put them all together and threw massive resources at it, but it wasn’t technically groundbreaking. When I say “A0 network types,” I mean the old familiar ResNet with chess state inputs and policy and value outputs. Nothing earthshaking about that, and value and ...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:53 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

one of the top Leela devs told me Ankan is the most important person in the project and although he spent little time contributing, his code is really critical as noone else knows to code for GPU, and without him cuda backend wouldn't probably happen . So for the record, you agree that the lc0 cuDN...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:44 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

If you run SIMEX on neural network engines (other than Stoofvlees), you get similarity of over 60%. That’s because they all derive from the alpha zero pseudo code which dictates certain neural network structures. IIRC, I saw some statements that SIMEX rates Stockfish and lc0 rather closely, more so...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:31 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

Haha, I just had an idea inspired by events that happened in other engine competitions (unrelated to chess), which didn't disallow engines by same author or clone engines. What you could do is entering to TCEC some hundred clones of Allie. Stoofvlees exists because at some point the CSVN thought it...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:25 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

They all use essentially the same A0 network types, as that is dictated by the PUCT search algorithm. Really? Well, you probably want at least a move probability and some kind of winrate eval. That's not even an A0 innovation, although Alpha Zero was the first time I saw the networks for those outp...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:22 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

P.S. Gian-Carlo: big fan of your work. Really curious to know what’s under the covers with Stoofvlees. Deep Sjeng, I thought that was somewhat obvious :D There's nothing really "special" inside Stoofvlees (yet?! I think I'll need something to surpass the lc0 family). Someone on TCEC chat called it ...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:16 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

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...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 5:12 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

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...
by Gian-Carlo Pascutto
Thu Sep 19, 2019 4:59 pm
Forum: Computer Chess Club: General Topics
Topic: My failed attempt to change TCEC NN clone rules
Replies: 92
Views: 9907

Re: My failed attempt to change TCEC NN clone rules

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 ...