Search found 565 matches

by D Sceviour
Tue Jan 05, 2021 11:52 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: How to calc the derivative for gradient descent?
Replies: 14
Views: 843

Re: How to calc the derivative for gradient descent?

The discussion about linearity in evaluation function is very bad. You might have a function that is linear with respect to your features, I.e. a linear combination of those features, but the features themselves might not be linear. You can also create a linear function of your highly non linear ev...
by D Sceviour
Tue Jan 05, 2021 10:08 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: How to calc the derivative for gradient descent?
Replies: 14
Views: 843

Re: How to calc the derivative for gradient descent?

Hello, this is my first post. I'd like to know which way you suggest for calculating the derivative of the evaluation for each parameter for gradient descent with Texel tuning. I've read about (Eval(xi+1)-Eval(xi-1))/2, Eval(xi+1)-Eval(xi), auto differentiation libraries, Jacobian matrix and so for...
by D Sceviour
Tue Jan 05, 2021 10:02 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: How to calc the derivative for gradient descent?
Replies: 14
Views: 843

Re: How to calc the derivative for gradient descent?

Hello, this is my first post. I'd like to know which way you suggest for calculating the derivative of the evaluation for each parameter for gradient descent with Texel tuning. I've read about (Eval(xi+1)-Eval(xi-1))/2, Eval(xi+1)-Eval(xi), auto differentiation libraries, Jacobian matrix and so for...
by D Sceviour
Tue Jan 05, 2021 5:00 pm
Forum: Computer Chess Club: Programming and Technical Discussions
Topic: How to calc the derivative for gradient descent?
Replies: 14
Views: 843

Re: How to calc the derivative for gradient descent?

Hello, this is my first post. I'd like to know which way you suggest for calculating the derivative of the evaluation for each parameter for gradient descent with Texel tuning. I've read about (Eval(xi+1)-Eval(xi-1))/2, Eval(xi+1)-Eval(xi), auto differentiation libraries, Jacobian matrix and so for...
by D Sceviour
Thu Dec 31, 2020 3:10 pm
Forum: Computer Chess Club: General Topics
Topic: Dispelling the Myth of NNUE with LazySMP: An Analysis
Replies: 39
Views: 1752

Re: Dispelling the Myth of NNUE with LazySMP: An Analysis

@Andrew sorry for this offspring about polyglot book dump (started by Denis), may be the thread could be split up? Andrews post should have been put in the programming section. @Michel No one ever answered my post about book dump not working correctly in most cases on Windows (at least). Note that ...
by D Sceviour
Thu Dec 31, 2020 3:00 pm
Forum: Computer Chess Club: General Topics
Topic: Dispelling the Myth of NNUE with LazySMP: An Analysis
Replies: 39
Views: 1752

Re: Dispelling the Myth of NNUE with LazySMP: An Analysis

OK! Got it. I will look at that maybe in the new year. My project for today is creating a program to disassemble polyglot books. Somebody said that program does not exist. If not, it will exist shortly. Look at the polyglot option dump-book. This may be what you want. Below some sample output. Dump...
by D Sceviour
Thu Dec 31, 2020 5:27 am
Forum: Computer Chess Club: General Topics
Topic: Dispelling the Myth of NNUE with LazySMP: An Analysis
Replies: 39
Views: 1752

Re: Dispelling the Myth of NNUE with LazySMP: An Analysis

AVX is on the agenda to look at. My hardware is supposed to handle it, but does it make that much difference? If you did not also update your makefile to match CFish, then you compiled basic forloops for everything, and the result was probably 5x slower than it should be. What is your NPS on Schoon...
by D Sceviour
Thu Dec 31, 2020 5:17 am
Forum: Computer Chess Club: General Topics
Topic: Dispelling the Myth of NNUE with LazySMP: An Analysis
Replies: 39
Views: 1752

Re: Dispelling the Myth of NNUE with LazySMP: An Analysis

AVX is on the agenda to look at. My hardware is supposed to handle it, but does it make that much difference? If you did not also update your makefile to match CFish, then you compiled basic forloops for everything, and the result was probably 5x slower than it should be. What is your NPS on Schoon...
by D Sceviour
Thu Dec 31, 2020 5:01 am
Forum: Computer Chess Club: General Topics
Topic: Dispelling the Myth of NNUE with LazySMP: An Analysis
Replies: 39
Views: 1752

Re: Dispelling the Myth of NNUE with LazySMP: An Analysis

Stockfish gained an inordinate amount of strength with the introduction of NNUE, as did all engines which have followed in Stockfish's footsteps. Not Schooner, which attempted the CFish NNUE port. Schooner achieved a large -40 elo loss. Work on NNUE has been abandoned for the moment, but I may look...
by D Sceviour
Thu Dec 31, 2020 4:42 am
Forum: Computer Chess Club: General Topics
Topic: Dispelling the Myth of NNUE with LazySMP: An Analysis
Replies: 39
Views: 1752

Re: Dispelling the Myth of NNUE with LazySMP: An Analysis

Stockfish gained an inordinate amount of strength with the introduction of NNUE, as did all engines which have followed in Stockfish's footsteps. Not Schooner, which attempted the CFish NNUE port. Schooner achieved a large -40 elo loss. Work on NNUE has been abandoned for the moment, but I may look...