Sciweavers

ICANN
2009
Springer

Scalable Neural Networks for Board Games

13 years 12 months ago
Scalable Neural Networks for Board Games
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.
Tom Schaul, Jürgen Schmidhuber
Added 25 Jul 2010
Updated 02 Aug 2010
Type Conference
Year 2009
Where ICANN
Authors Tom Schaul, Jürgen Schmidhuber
Comments (0)