Neural Foundations · 2014
Neural Turing Machines / Memory Networks
Graves et al. introduced the Neural Turing Machine, a neural network coupled to an external memory matrix it can read from and write to using differentiable attention, so the whole system can be trained by gradient descent to learn simple algorithms, addressing standard networks' limited ability to store and manipulate structured data over time.
Editorial record
Plain-language summary
A controller network emits read and write operations addressed to memory locations using soft, differentiable attention weights (based on content similarity and location shifting), so gradients can flow through the memory access and the model learns how to use its memory end-to-end. This separates computation from an addressable storage bank, letting the network learn procedures like copying, sorting, and associative recall and generalize them to longer inputs than seen in training. It, alongside Memory Networks, showed that networks augmented with external memory could learn algorithm-like behavior, influencing later memory-augmented and attention-based models.
Source record
Provenance
- Record ID
- A-037
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/1410.5401
- arXiv:1410.5401
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.