clanek_go_congress/clanek.tex

   1 \documentclass[12pt,a4paper]{report}
   2
   3 %% Použité kódování znaků: obvykle latin2, cp1250 nebo utf8:
   4 \usepackage[utf8]{inputenc}
   5
   6 %% Ostatní balíčky
   7 \usepackage[titletoc]{appendix}
   8 \usepackage{graphicx}
   9 \usepackage{wrapfig}
  10 \usepackage{color}
  11 \usepackage[multiple]{footmisc}
  12 \usepackage{amsthm}
  13 \usepackage{amsmath}
  14 \usepackage{threeparttable}
  15 \usepackage{longtable}
  16 \usepackage{tabularx}
  17 \usepackage{amsfonts}
  18 \usepackage{caption}
  19 \usepackage[lined, ruled, boxed, linesnumbered]{algorithm2e}
  20
  21 \usepackage[round]{natbib}             % sazba pouzite literatury
  22
  23 \usepackage{psfrag}
  24
  25 \usepackage{psgo,array}
  26 \usepackage{url}                % sazba URL
  27
  28 \usepackage[ps2pdf,unicode]{hyperref}   % Musí být za všemi ostatními balíčky
  29 \usepackage{breakurl}
  30
  31
  32 \hypersetup{pdftitle=Meta-learning methods for analyzing Go playing trends}
  33 \hypersetup{pdfauthor=Josef Moudřík}
  34
  35 \begin{document}
  36 %
  37 % paper title
  38 % can use linebreaks \\ within to get better formatting as desired
  39 \title{On Move Pattern Trends\\in  Large Go Games Corpus}
  40
  41 % use \thanks{} to gain access to the first footnote area
  42 % a separate \thanks must be used for each paragraph as LaTeX2e's \thanks
  43 % was not built to handle multiple paragraphs
  44 \author{Josef~Moud\v{r}\'{i}k,~Petr~Baudi\v{s}%
  45 \thanks{J. Moud\v{r}\'{i}k is student at the Faculty of Math and Physics, Charles University, Prague, CZ.}%
  46 \thanks{P. Baudi\v{s} is student at the Faculty of Math and Physics,
  47 Charles University, Prague, CZ, and also does some of his Computer
  48 Go research as an employee of SUSE Labs Prague, Novell CZ.}}
  49 \maketitle
  50
  51 \begin{abstract}
  52 %\boldmath
  53
  54 We propose a~way of extracting a per-move evaluation of sets of Go game records.
  55 The evaluations capture different aspects of the games such as patterns played
  56 or statistics of sente/gote sequences (among others); using machine learning
  57 algorithms, they can be used to predict arbitrary relevant target variables.
  58 We apply this methodology to predict strength and playing style
  59 (e.g. territoriality or aggressivity) of a player and realize this as an online
  60 tool as a part of the GoStyle project.
  61 By inspecting the dependencies between the evaluations and the target variable,
  62 we are able to tell which patterns are bad or good (in case of strength as the
  63 target variable), or which moves e.g. constitute the territorial style of play.
  64 We propose a number of possible applications including seeding real-work ranks
  65 of internet players, aiding in Go study and tuning of Go-playing programs, or
  66 contribution to Go-theoretical discussion on the scope of ``playing style''.
  67 \end{abstract}
  68
  69
  70 \end{document}