Learning Operations on a Stack with Neural Turing Machines
Machine Learning
2016-12-05 v1
Abstract
Multiple extensions of Recurrent Neural Networks (RNNs) have been proposed recently to address the difficulty of storing information over long time periods. In this paper, we experiment with the capacity of Neural Turing Machines (NTMs) to deal with these long-term dependencies on well-balanced strings of parentheses. We show that not only does the NTM emulate a stack with its heads and learn an algorithm to recognize such words, but it is also capable of strongly generalizing to much longer sequences.
Cite
@article{arxiv.1612.00827,
title = {Learning Operations on a Stack with Neural Turing Machines},
author = {Tristan Deleu and Joseph Dureau},
journal= {arXiv preprint arXiv:1612.00827},
year = {2016}
}
Comments
1st Workshop on Neural Abstract Machines & Program Induction (NAMPI), NIPS 2016, Barcelona, Spain