Methods › Sequential › Recurrent Neural Networks › LMU
Legendre Memory Unit
LMU
Introduced by Aaron Voelker et al. in Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Legendre Memory Unit (LMU) is mathematically derived to orthogonalize its continuous-time history – doing so by solving d coupled ordinary differential equations (ODEs), whose phase space linearly maps onto sliding windows of time via the Legendre polynomials up to degree d-1. It is optimal for compressing temporal information.
See paper for equations (markdown isn't working).
Official github repo: https://github.com/abr/lmu
Papers archive 2025-07-28
9 shown of 9, 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.
-
SynthRAD2025 Grand Challenge dataset: generating synthetic CTs for radiotherapy 24 Feb 2025 · 0 repositories · arXiv:2502.17609
-
Natively neuromorphic LMU architecture for encoding-free SNN-based HAR on commercial edge devices 4 Jul 2024 · 0 repositories · arXiv:2407.04076
-
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units 20 Jan 2024 · 1 repository · arXiv:2402.04882Syntology ran 9 of 12 samples · 3 unverified
-
Learning-Based Data Storage [Vision] (Technical Report) 12 Jun 2022 · 0 repositories · arXiv:2206.05778
-
Contrasting LMU with LSTM 17 Jan 2022 · 0 repositories
-
Parallelizing Legendre Memory Unit Training 22 Feb 2021 · 2 repositories · arXiv:2102.11417
-
Feedforward Legendre Memory Unit 1 Jan 2021 · 0 repositories
-
The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task 25 Oct 2020 · 1 repository · arXiv:2010.13192
-
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks 1 Dec 2019 · 2 repositories
Tasks archive 2025-07-28
20 shown of 24 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