@inproceedings{Schaul2009,
abstract = {Learning to solve small instances of a problem should help in solving large instances. Unfortunately, most neural network architectures do not exhibit this form of scalability. Our Multi-Dimensional Recurrent LSTM Networks, however, show a high degree of scalability, as we empirically show in the domain of flexible-size board games. This allows them to be trained from scratch up to the level of human beginners, without using domain knowledge.},
author = {Schaul, Tom and Schmidhuber, J\"{u}rgen},
booktitle = {International Conference on Artificial Neural Networks (ICANN)},
keywords = {Board Games,Evolution Strategies,Go,LSTM,MDRNN,Neural Networks,games,recurrent neural networks,scalability},
title = {Scalable Neural Networks for Board Games},
year = {2009}
}