Methods › General › Activation Functions › Hard Sigmoid
Hard Sigmoid
Introduced by Matthieu Courbariaux et al. in BinaryConnect: Training Deep Neural Networks with binary weights during propagations
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Hard Sigmoid is an activation function used for neural networks of the form:
f(x) = max(0, min(1,(x+1)/2))
Image Source: Rinat Maksutov
Papers archive 2025-07-28
4 shown of 4, 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.
-
K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation 18 May 2022 · 0 repositories · arXiv:2205.08671
-
MaskConvNet: Training Efficient ConvNets from Scratch via Budget-constrained Filter Pruning 1 Jan 2020 · 0 repositories
-
L₀-ARM: Network Sparsification via Stochastic Binary Optimization 9 Apr 2019 · 1 repository · arXiv:1904.04432
-
BinaryConnect: Training Deep Neural Networks with binary weights during propagations 2 Nov 2015 · 5 repositories · arXiv:1511.00363Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
Tasks archive 2025-07-28
4 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 |
|---|---|
| Clustering | 1 |
| Image Segmentation | 1 |
| Network Pruning | 1 |
| Semantic Segmentation | 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