Using neural network learning in an Othello evaluation function

Authors: Abdelbar A.M.; Tagliarini G. A.

Source: Journal of Experimental & Theoretical Artificial Intelligence, Volume 10, Number 2, 1 April 1998 , pp. 217-229(13)

Publisher: Taylor and Francis Ltd

Key:

- Free Content

- New Content

- Subscribed Content

- Free Trial Content

Abstract:

. Bayesian learning, a statisticalmethod, has been successfully applied to the feature combination stage of the evaluation function of the Othello program BILL, which won the 1989 North American Othello Championship. The use of a novel neural network referred to as HONEST in place of Bayesian learning in BILL, was investigated. The HONEST network was implemented in six of BILL's 26 evaluation functions and resulted in the percentage of misclassified positions being reduced by an average of about 20%.

Language: English

Document Type: Research article

The full text electronic article is available for purchase. You will be able to download the full text electronic article after payment.

$45.29 plus tax Refund Policy