Methods › General › Activation Functions › PReLU

Parameterized ReLU

PReLU

119 papers tagged archive 2025-07-28

Introduced by Kaiming He et al. in Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

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

A Parametric Rectified Linear Unit, or PReLU, is an activation function that generalizes the traditional rectified unit with a slope for negative values. Formally:

f(yᵢ) = yᵢ if yᵢ ≥0 f(yᵢ) = aᵢyᵢ if yᵢ ≤0

The intuition is that different layers may require different types of nonlinearity. Indeed the authors find in experiments with convolutional neural networks that PReLus for the initial layer have more positive slopes, i.e. closer to linear. Since the filters of the first layers are Gabor-like filters such as edge or texture detectors, this shows a circumstance where positive and negative responses of filters are respected. In contrast the authors find deeper layers have smaller coefficients, suggesting the model becomes more discriminative at later layers (while it wants to retain more information at earlier layers).

PaperSourceSee Code · pytorch/pytorch

In Syntology repository known, no verified implementation (declared_code; repositories: 5 listed of 15 in the graph, strongest link: mentioned on GitHub). The lookup matched a different name in Syntology's graph, 'Parametric Rectified Linear Unit (PReLU)' (resolution: alias); this answer is about that name. This answer is about arXiv:1502.01852, the paper the archive credits with this method.

Origin paper of this answer, arXiv:1502.01852 (its page on this site · its page on Syntology): Syntology's run record for its harvested code, 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence). The instrument figure counts failures of Syntology's instrument, not of the code. Ran means executed on a synthesized input, not that the code is correct.

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: 119 · with a code link: 53 · where Syntology ran a sample: 14 (12 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (14 of 119 tagged: 12 with a run with no instrument failure, 2 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 119, 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

20 shown of 116 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
Super-Resolution31
Image Super-Resolution21
Semantic Segmentation21
Segmentation14
Generative Adversarial Network12
Speech Recognition12
Speech Separation12
speech-recognition11
Automatic Speech Recognition9
SSIM9
Automatic Speech Recognition (ASR)8
Decoder6
Image Classification6
image-classification6
Autonomous Driving5
Speech Enhancement5
Object Detection4
Quantization4
Real-Time Semantic Segmentation4
object-detection4

Usage over time archive 2025-07-28

Papers per year tagged with PReLU: 2015 to 2025, peak 24 24 0 2015: 1 paper 2015 2016: 2 papers 2016 2017: 3 papers 2017 2018: 16 papers 2018 2019: 11 papers 2019 2020: 24 papers 2020 2021: 13 papers 2021 2022: 14 papers 2022 2023: 11 papers 2023 2024: 19 papers 2024 2025: 5 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (119 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

Activation Functions

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