Neural Random-Access Machines

@article{Kurach2016NeuralRM,
  title={Neural Random-Access Machines},
  author={Karol Kurach and Marcin Andrychowicz and Ilya Sutskever},
  journal={ERCIM News},
  year={2016},
  volume={2016}
}
In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine. It can manipulate and dereference pointers to an external variable-size random-access memory. The model is trained from pure input-output examples using backpropagation. We evaluate the new model on a number of simple algorithmic tasks whose solutions require pointer manipulation and dereferencing. Our results show that the proposed model can learn to solve algorithmic tasks of such… CONTINUE READING
Highly Cited
This paper has 64 citations. REVIEW CITATIONS
Related Discussions
This paper has been referenced on Twitter 38 times. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-10 of 49 extracted citations

64 Citations

0102020152016201720182019
Citations per Year
Semantic Scholar estimates that this publication has 64 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 17 references

Neural Turing Machines

View 4 Excerpts
Highly Influenced

Curriculum learning

Bengio, Yoshua, +5 authors Jason
In Proceedings of the 26th annual international conference on machine learning, • 2009
View 3 Excerpts
Highly Influenced

End-to-end memory networks

Sukhbaatar, Sainbayar, +5 authors Rob
arXiv preprint arXiv:1503.08895, • 2015
View 1 Excerpt

Similar Papers

Loading similar papers…