Corpus ID: 18507239

Predicting Moves in Chess using Convolutional Neural Networks

@inproceedings{Oshri2015PredictingMI,
  title={Predicting Moves in Chess using Convolutional Neural Networks},
  author={Barak Oshri},
  year={2015}
}

• Barak Oshri
• Published 2015

We used a three layer Convolutional Neural Network (CNN) to make move predictions in chess. The task was defined as a two-part classification problem: a piece-selector CNN is trained to score which white pieces should be made to move, and move-selector CNNs for each piece produce scores for where it should be moved. This approach reduced the intractable class space in chess by a square root. The networks were trained using 20,000 games consisting of 245,000 moves made by players with an ELO… Expand

cs231n.stanford.edu

Save to Library

Create Alert

Cite

Launch Research Feed