Meta-learning methods for analyzing Go playing trends
Thesis title in Czech: | Meta-učící metody pro analýzu trendů her Go |
---|---|
Thesis title in English: | Meta-learning methods for analyzing Go playing trends |
Key words: | Go, aproximace funkcí, strojové učení, evoluce ansámblů |
English key words: | Go, function approximation, machine learning, evolution of ensembles |
Academic year of topic announcement: | 2011/2012 |
Thesis type: | diploma thesis |
Thesis language: | angličtina |
Department: | Department of Theoretical Computer Science and Mathematical Logic (32-KTIML) |
Supervisor: | Mgr. Roman Neruda, CSc. |
Author: | hidden - assigned and confirmed by the Study Dept. |
Date of registration: | 15.12.2011 |
Date of assignment: | 15.12.2011 |
Confirmed by Study dept. on: | 04.10.2012 |
Date and time of defence: | 10.09.2013 00:00 |
Date of electronic submission: | 22.07.2013 |
Date of submission of printed version: | 25.07.2013 |
Date of proceeded defence: | 10.09.2013 |
Opponents: | RNDr. František Mráz, CSc. |
Guidelines |
The goal of the work is to study the possibilities of meta-learning in
the field of Go game playing trends analysis. The student will propose data mining algorithms for extracting information from large Go games databases, and he will explore possible application of meta-learning. The task is to predict general properties of game players, such as strength or aggressiveness. A web application realizing the proposed algorithms and enabling further data collection will be a part of this work. |
References |
[1] T. Hastie, R. Tibshirani, J. Friedman - The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer, 2009
[2] N. Jankowski, W. Duch, K. Grabczewski - Meta-Learning in Computational Intelligence, Springer, 2011 |