Methods › Sequential › Recurrent Neural Networks › QRNN
Quasi-Recurrent Neural Network
QRNN
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A QRNN, or Quasi-Recurrent Neural Network, is a type of recurrent neural network that alternates convolutional layers, which apply in parallel across timesteps, and a minimalist recurrent pooling function that applies in parallel across channels. Due to their increased parallelism, they can be up to 16 times faster at train and test time than LSTMs.
Given an input sequence 𝐗 ∈ℝ^(T×n) of T n-dimensional vectors 𝐱₁, …, 𝐱_T, the convolutional subcomponent of a QRNN performs convolutions in the timestep dimension with a bank of m filters, producing a sequence 𝐙 ∈ℝ^(T×m) of m-dimensional candidate vectors 𝐳ₜ. Masked convolutions are used so filters can not access information from future timesteps (implementing with left padding).
Additional convolutions are applied with separate filter banks to obtain sequences of vectors for the elementwise gates that are needed for the pooling function. While the candidate vectors are passed through a tanh nonlinearity, the gates use an elementwise sigmoid. If the pooling function requires a forget gate fₜ and an output gate oₜ at each timestep, the full set of computations in the convolutional component is then:
𝐙 = tanh(𝐖_z ∗ 𝐗) 𝐅 = σ(𝐖_f ∗ 𝐗) 𝐎 = σ(𝐖ₒ ∗ 𝐗)
where 𝐖_z, 𝐖_f, and 𝐖ₒ, each in ℝ^(k×n×m), are the convolutional filter banks and ∗ denotes a masked convolution along the timestep dimension. Dynamic average pooling by Balduzzi & Ghifary (2016) is used, which uses only a forget gate:
𝐡ₜ = 𝐟ₜ ⊙𝐡ₜ₋₁ + (1 − 𝐟ₜ) ⊙ 𝐳ₜ
Which is denoted f-pooling. The function may also include an output gate:
𝐜ₜ = 𝐟ₜ ⊙𝐜ₜ₋₁ + (1 − 𝐟ₜ) ⊙ 𝐳ₜ
𝐡ₜ = 𝐨ₜ ⊙𝐜ₜ
Which is denoted fo-pooling. Or the recurrence relation may include an independent input and forget gate:
𝐜ₜ = 𝐟ₜ ⊙𝐜ₜ₋₁ + 𝐢ₜ⊙ 𝐳ₜ
𝐡ₜ = 𝐨ₜ ⊙𝐜ₜ
Which is denoted ifo-pooling. In each case h or c is initialized to zero. The recurrent part sof these functions must be calculated for each timestep in the sequence, but parallelism along feature dimensions means evaluating them even over long sequences requires a negligible amount of computation time.
A single QRNN layer thus performs an input-dependent pooling, followed by a gated linear combination of convolutional features. As with convolutional neural networks, two or more QRNN layers should be stacked to create a model with the capacity to approximate more complex functions.
Papers archive 2025-07-28
15 shown of 15, 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.
-
Obtaining Optimal Spiking Neural Network in Sequence Learning via CRNN-SNN Conversion 18 Aug 2024 · 0 repositories · arXiv:2408.09403
-
Ensemble learning for predictive uncertainty estimation with application to the correction of satellite precipitation products 14 Mar 2024 · 0 repositories · arXiv:2403.10567
-
Uncertainty estimation of machine learning spatial precipitation predictions from satellite data 13 Nov 2023 · 0 repositories · arXiv:2311.07511
-
Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction 31 Oct 2023 · 0 repositories · arXiv:2310.20671
-
Efficient quantum recurrent reinforcement learning via quantum reservoir computing 13 Sep 2023 · 0 repositories · arXiv:2309.07339
-
Quantum Recurrent Neural Networks for Sequential Learning 7 Feb 2023 · 1 repository · arXiv:2302.03244
-
Time-Warping Invariant Quantum Recurrent Neural Networks via Quantum-Classical Adaptive Gating 19 Jan 2023 · 0 repositories · arXiv:2301.08173
-
Reservoir Computing via Quantum Recurrent Neural Networks 4 Nov 2022 · 0 repositories · arXiv:2211.02612
-
Rapid training of quantum recurrent neural networks 1 Jul 2022 · 1 repository · arXiv:2207.00378
-
TYolov5: A Temporal Yolov5 Detector Based on Quasi-Recurrent Neural Networks for Real-Time Handgun Detection in Video 17 Nov 2021 · 1 repository · arXiv:2111.08867
-
Cyber Threat Intelligence for Secure Smart City 26 Jul 2020 · 0 repositories · arXiv:2007.13233
-
A Formal Hierarchy of RNN Architectures 18 Apr 2020 · 0 repositories · arXiv:2004.08500
-
Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference 30 Mar 2018 · 0 repositories · arXiv:1803.11389
-
Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks 25 Jul 2017 · 2 repositories · arXiv:1707.08214
-
Quasi-Recurrent Neural Networks 5 Nov 2016 · 7 repositories · arXiv:1611.01576Syntology ran 0 of 1 samples · 1 unverified
Tasks archive 2025-07-28
20 shown of 34 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