Publication details

Probabilistic neural network playing a simple game

Conference Paper (international conference)

Grim Jiří, Somol Petr, Pudil Pavel, Just P.

serial: Artificial Neural Networks in Pattern Recognition. Proceedings, p. 132-138 , Eds: Marinai S., Gori M.

publisher: University of Florence, (Florence 2003)

action: IAPR TC3 Workshop 2003 /1./, (Florence, IT, 12.09.2003-13.09.2003)

research: CEZ:AV0Z1075907

project(s): GA402/01/0981, GA ČR, GA402/03/1310, GA ČR, KSK1019101, GA AV ČR

keywords: probabilistic neural networks, finite mixtures, EM algorithm

abstract (eng):

The goal of the paper is to design a probabilistic neural network playing a simple two-player game "Tic-Tac-Toe". The game is considered as a problem of a repeating evaluation of preferences of possible moves. Assuming the probabilistic neural network in the role of the evaluation function we can solve the problem by estimating the probability distribution of advantageous moves. The unknown distribution is estimated in the form of a finite discrete mixture of product components by means of EM algorithm.

Cosati: 12B, 06D