Methods › Sequential › Recurrent Neural Networks › Neural Turing Machine
Neural Turing Machine
Introduced by Alex Graves et al. in Neural Turing Machines
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Neural Turing Machine is a working memory neural network model. It couples a neural network architecture with external memory resources. The whole architecture is differentiable end-to-end with gradient descent. The models can infer tasks such as copying, sorting and associative recall.
A Neural Turing Machine (NTM) architecture contains two basic components: a neural network controller and a memory bank. The Figure presents a high-level diagram of the NTM architecture. Like most neural networks, the controller interacts with the external world via input and output vectors. Unlike a standard network, it also interacts with a memory matrix using selective read and write operations. By analogy to the Turing machine we refer to the network outputs that parameterise these operations as “heads.”
Every component of the architecture is differentiable. This is achieved by defining 'blurry' read and write operations that interact to a greater or lesser degree with all the elements in memory (rather than addressing a single element, as in a normal Turing machine or digital computer). The degree of blurriness is determined by an attentional “focus” mechanism that constrains each read and write operation to interact with a small portion of the memory, while ignoring the rest. Because interaction with the memory is highly sparse, the NTM is biased towards storing data without interference. The memory location brought into attentional focus is determined by specialised outputs emitted by the heads. These outputs define a normalised weighting over the rows in the memory matrix (referred to as memory “locations”). Each weighting, one per read or write head, defines the degree to which the head reads or writes at each location. A head can thereby attend sharply to the memory at a single location or weakly to the memory at many locations
Papers archive 2025-07-28
22 shown of 22, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Intelligent DoS and DDoS Detection: A Hybrid GRU-NTM Approach to Network Security 10 Apr 2025 · 0 repositories · arXiv:2504.07478
-
Memory-augmented conformer for improved end-to-end long-form ASR 22 Sep 2023 · 1 repository · arXiv:2309.13029
-
FashionNTM: Multi-turn Fashion Image Retrieval via Cascaded Memory 20 Aug 2023 · 0 repositories · arXiv:2308.10170
-
Token Turing Machines 16 Nov 2022 · 1 repository · arXiv:2211.09119
-
Unsupervised Speaker Adaptation using Attention-based Speaker Memory for End-to-End ASR 14 Feb 2020 · 0 repositories · arXiv:2002.06165
-
Memory-Augmented Recurrent Networks for Dialogue Coherence 16 Oct 2019 · 0 repositories · arXiv:1910.10487
-
A Neural Turing~Machine for Conditional Transition Graph Modeling 15 Jul 2019 · 0 repositories · arXiv:1907.06432
-
Understanding Memory Modules on Learning Simple Algorithms 1 Jul 2019 · 0 repositories · arXiv:1907.00820
-
A review on Neural Turing Machine 10 Apr 2019 · 0 repositories · arXiv:1904.05061
-
Few-Shot Generalization Across Dialogue Tasks 28 Nov 2018 · 2 repositories · arXiv:1811.11707
-
Context-Aware Neural Model for Temporal Information Extraction 1 Jul 2018 · 0 repositories
-
A Taxonomy for Neural Memory Networks 1 May 2018 · 0 repositories · arXiv:1805.00327
-
Meta-Learning via Feature-Label Memory Network 19 Oct 2017 · 0 repositories · arXiv:1710.07110
-
Attention-Set based Metric Learning for Video Face Recognition 12 Apr 2017 · 0 repositories · arXiv:1704.03805
-
Tracking the World State with Recurrent Entity Networks 12 Dec 2016 · 5 repositories · arXiv:1612.03969Syntology ran 0 of 3 samples · 3 unverified
-
Neural Turing Machines: Convergence of Copy Tasks 7 Dec 2016 · 0 repositories · arXiv:1612.02336
-
Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes 30 Jun 2016 · 0 repositories · arXiv:1607.00036
-
Lie Access Neural Turing Machine 28 Feb 2016 · 0 repositories · arXiv:1602.08671
-
Empirical Study on Deep Learning Models for Question Answering 26 Oct 2015 · 0 repositories · arXiv:1510.07526
-
A Deep Memory-based Architecture for Sequence-to-Sequence Learning 22 Jun 2015 · 0 repositories · arXiv:1506.06442
-
Reinforcement Learning Neural Turing Machines - Revised 4 May 2015 · 1 repository · arXiv:1505.00521
-
Neural Turing Machines 20 Oct 2014 · 34 repositories · arXiv:1410.5401Syntology ran 4 of 8 samples · 4 unverified · 2 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 32 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections