Authors:
Matthia Sabatelli
1
;
Francesco Bidoia
2
;
Valeriu Codreanu
3
and
Marco Wiering
2
Affiliations:
1
University of Groningen and Université de Liège, Netherlands
;
2
Université de Liège, Belgium
;
3
Surfsara BV, Netherlands
Keyword(s):
Artificial Neural Networks, Classification, Regression, Chess Patterns, Deep Learning.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Classification
;
Computer Vision, Visualization and Computer Graphics
;
Geometry and Modeling
;
Image-Based Modeling
;
Pattern Recognition
;
Regression
;
Software Engineering
;
Theory and Methods
Abstract:
In this paper we propose a novel supervised learning approach for training Artificial Neural Networks (ANNs)
to evaluate chess positions. The method that we present aims to train different ANN architectures to understand
chess positions similarly to how highly rated human players do. We investigate the capabilities that ANNs
have when it comes to pattern recognition, an ability that distinguishes chess grandmasters from more amateur
players. We collect around 3,000,000 different chess positions played by highly skilled chess players and label
them with the evaluation function of Stockfish, one of the strongest existing chess engines. We create 4 different
datasets from scratch that are used for different classification and regression experiments. The results show
how relatively simple Multilayer Perceptrons (MLPs) outperform Convolutional Neural Networks (CNNs) in
all the experiments that we have performed. We also investigate two different board representations, the first
o
ne representing if a piece is present on the board or not, and the second one in which we assign a numerical
value to the piece according to its strength. Our results show how the latter input representation influences the
performances of the ANNs negatively in almost all experiments.
(More)