Methods › Sequential › Recurrent Neural Networks › Unitary RNN

Unitary RNN

3 papers tagged archive 2025-07-28

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

PaperSource

In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.

Near matches the lookup lists, each a different name: MMP-RNN; M 2 RNN; SITH-RNN; Decay RNN; LLM-as-RNN; RNN-Maxent; Lipschitz RNN; Fixed-Pole RNN.

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 3 · with a code link: 2 · where Syntology ran a sample: 1 (1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (1 of 3 tagged: 1 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 3 of 3, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

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.

TaskPapers
AutoML1
Marketing1
Multimodal Sentiment Analysis1
Recommendation Systems1
Sentiment Analysis1
Sequential Image Classification1

Usage over time archive 2025-07-28

Papers per year tagged with Unitary RNN: 2015 to 2021, peak 1 1 0 2015: 1 paper 2015 2016: 0 papers 2016 2017: 0 papers 2017 2018: 1 paper 2018 2019: 0 papers 2019 2020: 0 papers 2020 2021: 1 paper 2021
Papers per year the archive tags with this method, by the paper's archive date (3 dated). 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

Recurrent Neural Networks

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