TalkChess.com

* more info for rule 1: Using too many neurons in the hidden layers can result in several problems. First, too many neurons in the hidden layers may result in overfitting. Overfitting occurs when the neural network has so much information processing capacity that the limited amount of information c...

Since I am developing in JavaScript, I train the neural network in NodeJS. Training with own writed Neural Network, I don't use machine learning platform. This is very slow and by far not the best choice. This forced me to experiment with alternative solutions. I wanted to get the best results as qu...

Hi @gladius: have you tried a method similar to mine? http://talkchess.com/forum3/viewtopic.php?f=7&t=75925#p874604 I mean, the target(output) is pre-activated. I am currently trying with few samples. But I have already won a few elo. Because my hardware is limited, I don’t want to waste time unnece...

- pure javascript implementation of GUI (HTML table) What I like about your GUI is that you can drag the piece images. The Interactive Diagram lost that capability when I started displaying the pieces as background image. And even before that it did not work as well as in your case. Is this because...

I'm thinking about providing a simple alpha beta search to play against as well, but I'm having problems with negative indices in TT when hash key is negative. I know I can make it unsigned via Uint32Array([hash_key])[0] but when hash key gets incrementally updated it gets to negative values from t...

I'm thinking about providing a simple alpha beta search to play against as well, but I'm having problems with negative indices in TT when hash key is negative. I know I can make it unsigned via Uint32Array([hash_key])[0] but when hash key gets incrementally updated it gets to negative values from t...

In Ethereal, ``pkeval`` refers to the evaluation of Pawns + Kings, without knowledge of any Rooks, Knights, Bishops, or Queens on the board. It is a function of only Pawns and Kings, and as a result can be placed into the Pawn+King Hash table. Passed pawns take into account other factors, like safe...

Hi! My PK networks were a bit strange in how you trained them. They would train the output, to add to a static eval, if a position, using a sigmoid loss function. I never actually replaced my King+Pawn evaluation with the Neural Network, I simply augmented it. Yes i would train the output but only t...

I'm trying to add a Pawn King Neural Network (like Ethereal) to my JavaScript chess engine. What i do: 1.) Extract pawn king eval for 0.7M position at depth 6. (cp eval for MG and EG) 2.) Befor training eval all positions with qsearch same as like above. 3.) During 2. point fill a input array with p...

Sorry, the links was wrong. Here is the free apps:

iOS: https://apps.apple.com/us/app/sakk/id1150654415
Android: https://play.google.com/store/apps/deta ... k.tanky.hu