AWhat changed
Defined a smooth input-weighted activation through the expected action of an input-dependent stochastic identity/zero map, with Gaussian cumulative probabilities and empirical neural-network evaluations.
Scientific scope
Defined a smooth input-weighted activation through the expected action of an input-dependent stochastic identity/zero map, with Gaussian cumulative probabilities and empirical neural-network evaluations. Original2016v1 title differs from later Gaussian Error Linear Units title. The deterministic expected map is not dropout randomness during inference; its Gaussian motivation is not a guarantee that every layer is normally distributed. No universal superiority, earliest claim for every sigmoid-weighted variant or independent approximation-theorem certification.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Original2016v1 title differs from later Gaussian Error Linear Units title. The deterministic expected map is not dropout randomness during inference; its Gaussian motivation is not a guarantee that every layer is normally distributed. No universal superiority, earliest claim for every sigmoid-weighted variant or independent approximation-theorem certification.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
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