ML Anthology

Neural Stored-Program Memory

Hung Le, Truyen Tran, Svetha Venkatesh
ICLR 2020
/iclr/2020/le2020iclr-neural/

Abstract

Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern computer architectures. The proposed model, dubbed Neural Stored-program Memory, augments current memory-augmented neural networks, creating differentiable machines that can switch programs through time, adapt to variable contexts and thus fully resemble the Universal Turing Machine. A wide range of experiments demonstrate that the resulting machines not only excel in classical algorithmic problems, but also have potential for compositional, continual, few-shot learning and question-answering tasks.

PDF ICLR Semantic Scholar

Cite

Text

Le et al. "Neural Stored-Program Memory." International Conference on Learning Representations, 2020.

Markdown

[Le et al. "Neural Stored-Program Memory." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/le2020iclr-neural/)

BibTeX

@inproceedings{le2020iclr-neural,
  title     = {{Neural Stored-Program Memory}},
  author    = {Le, Hung and Tran, Truyen and Venkatesh, Svetha},
  booktitle = {International Conference on Learning Representations},
  year      = {2020},
  url       = {https://mlanthology.org/iclr/2020/le2020iclr-neural/}
}