REVIEW 3 cited by
Squareplus: A Softplus-Like Algebraic Rectifier
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present squareplus, an activation function that resembles softplus, but which can be computed using only algebraic operations: addition, multiplication, and square-root. Because squareplus is ~6x faster to evaluate than softplus on a CPU and does not require access to transcendental functions, it may have practical value in resource-limited deep learning applications.
Forward citations
Cited by 3 Pith papers
-
The Optimal Smoothings of Sublinear Functions and Convex Cones
For every sublinear function and convex cone, the paper characterizes all optimally smooth approximations as the interval between two explicit extremal smoothings.
-
Gradient Networks for Universal Magnetic Modeling of Synchronous Machines
A gradient-network model trained on sparse flux-linkage/current data reproduces the saturable, angle-periodic magnetic maps of a 5.6-kW synchronous machine while enforcing reciprocity, convexity, and smoothness by con...
-
Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials
Neural Cone Radiosity adds reflectance-aware ray cone encoding and clustering to neural radiosity, improving glossy reflection fidelity at interactive frame rates.
Discussion (0). Sign in to comment.