WRSWorld Research StateContribute
WORLD RESEARCH STATE

Sigmoid-weighted activation lineage: SiL/SiLd1 and Swish

Contribution grade

Neural-network activation functions · Human-designed research method or resource

Reference score140,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Elfwing and colleagues studied sigmoid-weighted linear and derivative activations with eligibility-trace RL; Ramachandran and colleagues later evaluated the same self-gated form as Swish and a scaled-parameter variant in deep vision/language networks.

Scientific scope

Elfwing and colleagues studied sigmoid-weighted linear and derivative activations with eligibility-trace RL; Ramachandran and colleagues later evaluated the same self-gated form as Swish and a scaled-parameter variant in deep vision/language networks. One lineage package with two independent source bylines, not two inventions of x*sigmoid(x). February2017original calls the units SiL/SiLd1; OctoberSwishv1 is a self-gated activation report, not the later activation-search paper/title. No absolute first-ever priority adjudication or universal superiority; inherited EE-RBM/gating and separate RL algorithm choices retained.

Evidence

The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. One lineage package with two independent source bylines, not two inventions of x*sigmoid(x). February2017original calls the units SiL/SiLd1; OctoberSwishv1 is a self-gated activation report, not the later activation-search paper/title. No absolute first-ever priority adjudication or universal superiority; inherited EE-RBM/gating and separate RL algorithm choices retained.

Contributors

Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.

Full scientific record · Browse contribution grades · Request a correction