Authors
Wojciech Zaremba, Ilya Sutskever
Publication date
2015/5
Journal
arXiv preprint arXiv:1505.00521
Volume
362
Description
Abstract The expressive power of a machine learning model is closely related to the number
of sequential computational steps it can learn. For example, Deep Neural Networks have
been more successful than shallow networks because they can perform a greater number of
sequential computational steps (each highly parallel). The Neural Turing Machine (NTM)[8]
is a model that can compactly express an even greater number of sequential computational
steps, so it is even more powerful than a DNN. Its memory addressing operations are ...
of sequential computational steps it can learn. For example, Deep Neural Networks have
been more successful than shallow networks because they can perform a greater number of
sequential computational steps (each highly parallel). The Neural Turing Machine (NTM)[8]
is a model that can compactly express an even greater number of sequential computational
steps, so it is even more powerful than a DNN. Its memory addressing operations are ...
Total citations
Scholar articles
W Zaremba, I Sutskever - arXiv preprint arXiv:1505.00521, 2015
Dates and citation counts are estimated and are determined automatically by a computer program.