Reinforcement Learning Neural Turing Machines

@article{Zaremba2015ReinforcementLN,
  title={Reinforcement Learning Neural Turing Machines},
  author={Wojciech Zaremba and Ilya Sutskever},
  journal={CoRR},
  year={2015},
  volume={abs/1505.00521}
}
The expressive power of a machine learning model is closely r elated to the number of sequential computational steps it can learn. For exam ple, Deep Neural Networks have been more successful than shallow networks be caus they can perform a greater number of sequential computational steps (ea ch highly parallel). The Neural Turing Machine (NTM) [8] is a model that can compac tly express an even greater number of sequential computational steps, so i t is even more powerful than a DNN. Its memory… CONTINUE READING
Highly Cited
This paper has 168 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 85 extracted citations

169 Citations

020406020152016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 169 citations based on the available data.

See our FAQ for additional information.