TalkChess.com

Igel 3.0.0 is ahead of Houdini 6 at the rating list. It's now in 3th place ( I don' t count the Stockfish clone Fat Fritz). Congratulations to Volodymyr Shcherbyna and Dietrich Kappe. It's not statistically significant yet to say that Igel is better than Houdini in 40/15. The elo difference between...

Frank, your discussion about chess GUIs and neural networks is off topic. I kindly ask you to start a new discussion about that.

More comments from the other thread from somebody who missed my comment: What exactly is the incentive to help people who come into the forum working on their first ever move generator? Obviously its a kind thing to do. If someone who knows all the tricks of the trade thinks himself to be too good t...

Oh? Did you care before, and what made you change your mind? It seems that what you care about isn't really that important, on the scale of things. I actually would think it is of exactly zero importance. What matters is if engine would gain a couple of hundred Elo by using a net architecture adapt...

Pedone 3 SF12 -> RMS=69.88 | SIM=43.26 SF13 -> RMS=70.18 | SIM=42.74 Halogen 10 SF12 -> RMS=70.54 | SIM=49.25 SF13 -> RMS=71.62 | SIM=49.49 Marvin 5 SF12 -> RMS=86.92 | SIM=48.81 SF13 -> RMS=87.44 | SIM=49.76 Seer 1.2.1 SF12 -> RMS=107.47 | SIM=36.27 SF13 -> RMS=108.57 | SIM=36.69 . Tornado support...

Frank Quisinsky wrote: ↑

Sat Mar 13, 2021 8:44 pm

And what is bad if programmers "copy the nodchip NNUE architecture into their engine" ??

It is only bad if you are like H.G. Muller and want to see engines use a neural network architecture that is designed specifically for chess and not for shogi. I personally no longer care either way.

Are these programmers on TalkChess? I must have missed their postings, then... BBC author: Maksim Korsh. Igel author: voffka. Rubichess author: RubiChess. Nemorino author: Florentino. Marvin author: Martin. All of them have been active members of Talkchess for the past few years and have posted and...

Hilarious that you have to draw on mclane as your principal example. The guy is not even a programmer. My principal example I gave in my last comment was not mclane, it was all those programmers on Talkchess who chose to copy the nodchip NNUE architecture into their engine; i.e. the authors of engi...

Note that nets trained on non-stockfish data often have to have their scores multiplied by a factor in order to fall into a good range for alpha-beta. Values between 1.5 to 2.5 are common. I use a python script to adjust the final layer for this. The toga net used a 1.55 multiplier, if I recall. If...

This discussion has gone off the original topic, so I have broken this topic off into a different topic entirely: http://talkchess.com/forum3/viewtopic.php?f=2&t=76858

Continue talking about rating lists and clones.