Methods › Sequential › Recurrent Neural Networks › Unitary RNN
Unitary RNN
Introduced by Martin Arjovsky et al. in Unitary Evolution Recurrent Neural Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Unitary RNN is a recurrent neural network architecture that uses a unitary hidden to hidden matrix. Specifically they concern dynamics of the form:
hₜ = f(Whₜ₋₁ + Vxₜ)
where W is a unitary matrix (W^†W = I). The product of unitary matrices is a unitary matrix, so W can be parameterised as a product of simpler unitary matrices:
hₜ = f(D₃R₂F⁻¹D₂PR₁FD₁hₜ₋₁ + Vxt)
where D₃, D₂, D₁ are learned diagonal complex matrices, and R₂, R₁ are learned reflection matrices. Matrices F and F⁻¹ are the discrete Fourier transformation and its inverse. P is any constant random permutation. The activation function f(h) applies a rectified linear unit with a learned bias to the modulus of each complex number. Only the diagonal and reflection matrices, D and R, are learned, so Unitary RNNs have fewer parameters than LSTMs with comparable numbers of hidden units.
Source: Associative LSTMs
Papers archive 2025-07-28
3 shown of 3, 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.
-
An AutoML-based Approach to Multimodal Image Sentiment Analysis 16 Feb 2021 · 0 repositories · arXiv:2102.08092
-
Complex Unitary Recurrent Neural Networks using Scaled Cayley Transform 9 Nov 2018 · 1 repository · arXiv:1811.04142
-
Unitary Evolution Recurrent Neural Networks 20 Nov 2015 · 2 repositories · arXiv:1511.06464Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
Tasks archive 2025-07-28
6 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| AutoML | 1 |
| Marketing | 1 |
| Multimodal Sentiment Analysis | 1 |
| Recommendation Systems | 1 |
| Sentiment Analysis | 1 |
| Sequential Image Classification | 1 |
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