Neural networks in chess programming

[hgm]

Thank you, I will have a look at it. Indeed one of the major challenges for developing the Interactive Diagram / Play-Test Applet is to find simple formal ways for describing game rules. My scope is limited to chess variants, and that of course simplifies matters somewhat.

[chesskobra]

Here are some notes on it. http://ggp.stanford.edu/notes/ (There is a pdf with all notes as well.)

[towforce]

This might interest you: https://en.wikipedia.org/wiki/Game_Description_Language The idea, if I am not mistaken, is to separate game description from the program that plays the game, so the program should be able to read the rules at run time, and play by the rules.

Let's see... a language in which one can describe a wide range of concepts... hmmmm.... Oh - I've got it - English!

It is said that human language and conceptualisation is rubbish for learning quantum physics, though. I haven't studied QP myself, but someone who has told me that you have to spend 6 months learning a new set of rules/concepts before you can really start learning the subject, and it makes no sense in terms of normal everyday concepts.