Number of the records: 1
Probabilistic neural network playing a simple game
- 1.
SYSNO ASEP 0411134 Document Type C - Proceedings Paper (int. conf.) R&D Document Type Conference Paper Title Probabilistic neural network playing a simple game Author(s) Grim, Jiří (UTIA-B) RID, ORCID
Somol, Petr (UTIA-B) RID
Pudil, Pavel (UTIA-B) RID
Just, P. (CZ)Issue data Florence: University of Florence, 2003 Source Title Artificial Neural Networks in Pattern Recognition. Proceedings / Marinai S. ; Gori M. Pages s. 132-138 Number of pages 7 s. Action IAPR TC3 Workshop 2003 /1./ Event date 12.09.2003-13.09.2003 VEvent location Florence Country IT - Italy Event type WRD Language eng - English Country IT - Italy Keywords probabilistic neural networks ; finite mixtures ; EM algorithm Subject RIV BB - Applied Statistics, Operational Research R&D Projects GA402/01/0981 GA ČR - Czech Science Foundation (CSF) GA402/03/1310 GA ČR - Czech Science Foundation (CSF) KSK1019101 GA AV ČR - Academy of Sciences of the Czech Republic (AV ČR) CEZ AV0Z1075907 - UTIA-B Annotation 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. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201.
Number of the records: 1