TalkChess.com

The reason for making a book based on games is usually that you don't trust engines to recognize the strategic aspects of the positions. Otherwise you might as well not bother, and let the engine play without book. This is true. Although books have another function which is to introduce variance fo...

The reason for making a book based on games is usually that you don't trust engines to recognize the strategic aspects of the positions. Otherwise you might as well not bother, and let the engine play without book. This is true. Although books have another function which is to introduce variance fo...

Can it beat this guy though who solves 17x17x17 cube in about 2 hours ? https://www.youtube.com/watch?v=7ChuKKL2PpU I would like to understand what makes it a unique challenge. From what I understood from the abstract - single goal state - solved in reverse with root node being that single goal sta...

I think chess NN is easier than general image classification that has the goal of identifying unlimited number of image classes. Maybe some of them can classify to a 1000 classes but then it won't be enough. For us, though we always have a fixed number of classes in value/policy head. I do not know...

Maybe leela nets will be public domain someday..after all they are generated by the gpu power of the people. I think for Go, facebook and others have provided strong networks for free but no one has done the same for chess other than lc0. If i start a training project (after i get a home gpu machin...

... something along the lines of say, ResNet50, a massively trained chess tower that programmers could remove the head of, add some layers, and take advantage of the knowledge patterns, hopefully generalized.

Public domain of course.

Book theory is unimportant. Moves and plan in a game count. I still think LC0 versus stockfish is boring, Stockfish is too stupid. Let stockfish compete versus Komodo or Houdini. They deserve it, But LC0 is about chess. And not about elo shit, Put LCZero on nodes=0 or 1 and SF at fixed depth 7 or 8...

I downloaded 2017 to current without any problem apart from huge amount of data. It takes several days here in rural France with slow and unreliable internet. The files, btw, get rejected as too large by memory sticks, so bear in mind how you're going to transfer them between PCs. It's possible som...

All the downloads failed at the very end for me (using FireFox derivative PaleMoon). But I did something underhanded to find the absolute address and downloaded them using wget (I was nice, one at a time). I know you want to enforce your own interface, but I figured you would not get mad since I tr...

Assuming infinite budget I score low on perfectionism so no need to discussie with me As soon as we move beyond alpha-beta in pruning, perfection has gone out the window. There never was any perfection, since the default is to prune at the horizon (depth). Pruning sacrifices some of the (otherwise ...