TalkChess.com

Thanks for testing FabChess!

Thanks for testing the newest version of FabChess, very good results aswell, basically on par with Asymptotes newest rating!

Thanks for the tournament Graham! Fab did pretty well in my opinion!

I have a new version of Fabchess at: https://github.com/fabianvdW/FabChess/releases/tag/v.1.13 This version increases the playing strength of Fabchess, preparing its appearance in TCEC. Changes done: - Decrease LMR - Restructure the Transposition Table. New replacement schema and introduce buckets. ...

If you try the history scores indexed by ply, let me know how this worked out for you Vivien, this has been on my "Try THIS" list for along time now and I haven't come around to do it... But hearing what bob has said maybe it would be more sensible to have history scores indexed by subtree, but this...

Well, the weights ('eval parameters') in a conventional evaluation are usually tuned, e.g. by Texel tuning. In fact the back-propagation used in a NN is nothing but Texel tuning of the NN. So my answer still stands. I like that you bring this up, because most are not aware of the similarity of the ...

Stockish does use a raw board representation as input for the evaluation, doesn't it? I think what Fabian was saying was that, in order to get a NN to evaluate a chess position reasonably well with just a few hundred weights you're proposing that, in your words, "The weights are piece (or piece-squ...

It depends on how you define "very well". If you are happy with Stockfish, the answer is "a couple of hundred". Conventional evaluations can be implemented as Neural networks with a one or two layers. The weights are piece (or piece-square) values, passer bonuses etc. If you are happy with micro-Ma...

Thanks Graham, very nice tournament!

Congrats to Luigi and ECE for having made quite the comeback in the later half of the tournament

Thanks a lot for testing FabChess