| Document Date: 2008-09-29 06:15:16
Open Document File Size: 544,60 KBShare Result on Facebook
City Tokyo / Porto / Munich / San Francisco / Manno-Lugano / Cambridge / / Company Neural Information Processing Systems / Pearson / Artificial Neural Networks / Multidimensional Recurrent Neural Networks / MIT Press / G. Tesauro / TRAINED NETWORKS / Atari / Ishi Press / Convolutional Networks / J. Alspector / Simultaneous Recurrent Networks / J. D. Cowan / Recurrent Neural Networks / / Country Germany / Switzerland / Japan / Portugal / / Currency ZAR / / / IndustryTerm search-based methods / search-based framework / feedforward network / search tree / particular algorithm / random networks / using traditional search-based methods / / MusicAlbum Play the Game / / Organization Federal Government / MIT / / Person Julian Togelius / D. Competitive / Faustino Gomez / Morgan Kaufmann / / Position first player / queen / random player / naive player / fixed value wb / wb / player / white player / / PublishedMedium Journal of Machine Learning Research / IEEE Transactions on Evolutionary Computation / Journal of Artificial Intelligence Research / / RadioStation CIAO / / Technology particular algorithm / Neural Network / machine learning / / URL http /
SocialTag |
A Scalable Neural Network Architecture for Board Games Tom Schaul, J¨urgen Schmidhuber Abstract— This paper proposes to use Multi-dimensional Recurrent Neural Networks (MDRNNs) as a way to overcome one of the key prob