Methods › General › Working Memory Models › Memory Network

Memory Network

445 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

A Memory Network provides a memory component that can be read from and written to with the inference capabilities of a neural network model. The motivation is that many neural networks lack a long-term memory component, and their existing memory component encoded by states and weights is too small and not compartmentalized enough to accurately remember facts from the past (RNNs for example, have difficult memorizing and doing tasks like copying).

A memory network consists of a memory m (an array of objects indexed by mᵢ and four potentially learned components:

Given an input x (e.g., an input character, word or sentence depending on the granularity chosen, an image or an audio signal) the flow of the model is as follows:

  1. Convert x to an internal feature representation I(x).
  2. Update memories mᵢ given the new input: mᵢ = G(mᵢ, I(x), m), ∀i.
  3. Compute output features o given the new input and the memory: o = O(I(x), m).
  4. Finally, decode output features o to give the final response: r = R(o).

This process is applied at both train and test time, if there is a distinction between such phases, that is, memories are also stored at test time, but the model parameters of I, G, O and R are not updated. Memory networks cover a wide class of possible implementations. The components I, G, O and R can potentially use any existing ideas from the machine learning literature.

Image Source: Adrian Colyer

Source: Memory NetworksSee Code · aykutaaykut/Memory-Networks

Papers archive 2025-07-28

30 shown of 445, 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.

Tasks archive 2025-07-28

20 shown of 386 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Question Answering37
Time Series28
General Classification26
Semantic Segmentation26
Prediction23
Time Series Analysis23
Decoder21
Video Semantic Segmentation21
Object20
Sentence20
Video Object Segmentation19
Classification18
Segmentation18
Language Modelling17
Retrieval16
Sentiment Analysis15
Language Modeling14
Deep Learning13
Decision Making12
Representation Learning11

Usage over time archive 2025-07-28

Papers per year tagged with Memory Network: 2014 to 2025, peak 79 79 0 2014: 1 paper 2014 2015: 2 papers 2015 2016: 11 papers 2016 2017: 29 papers 2017 2018: 47 papers 2018 2019: 74 papers 2019 2020: 52 papers 2020 2021: 79 papers 2021 2022: 45 papers 2022 2023: 42 papers 2023 2024: 37 papers 2024 2025: 25 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (444 dated, 1 undated not charted). Bars are counts, not a trend claim.

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

Working Memory Models

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