BrainKing - Tartışma Komiteleri (Chess variants (10x8))

Moderatör:

Chess variants (10x8)

Sam has closed his piano and gone to bed ... now we can talk about the real stuff of life ... love, liberty and games such as
Janus, Capablanca Random, Embassy Chess & the odd mention of other 10x8 variants is welcome too

For posting:
- invitations to games (you can also use the New Game menu or for particular games: Janus; Capablanca Random; or Embassy)
- information about upcoming tournaments
- disussion of games (please limit this to completed games or discussion on how a game has arrived at a certain position
... speculation on who has an advantage or the benefits of potential moves is not permitted while that particular game is in progress)
- links to interesting related sites (non-promotional)

Tartışma komitesi listesi

Durum: Herkes yazabilir

Önce en eski mesajı göster

18. Ekim 2004, 14:31:11

Grim Reaper

bu kullanıcının mesajlarını göster | Bağlantı

Konu: Learning function for Vortex

There is a way to "learn". Our very intelligent checkers program (a 154 MB download!) which is available here makes use of learning.

The problem is how to get the "learned data" from an end user's hard drive back to us so we can "pool the learning" and make it available for all to access.

Also, the learning function requires the end user to allow the program to perform some analysis on itself after the game. This can take anywhere from a few hours to a few days, depending on the complexity of the variations. This is something that cannot be "enforced", so we would have to figure out how to do this. Perhpas we could have the users upload their wins, and we would have a dedicated system that did all of the "learning".