AWhat changed
Designed scaled exponential-linear activations and compatible initialization to attract layerwise activation mean/variance toward a stable region under an analyzed moment map.
Scientific scope
Designed scaled exponential-linear activations and compatible initialization to attract layerwise activation mean/variance toward a stable region under an analyzed moment map. General ML architecture despite author affiliation and incidental application examples; no biological results entered. Moment analysis uses independent/common-moment inputs and Gaussian preactivation approximation with bounded parameter regions. Not universal self-normalization for arbitrary correlated architectures/weights, nor proof that all gradients can never vanish or explode. Only selected pages of102pagev1read.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. General ML architecture despite author affiliation and incidental application examples; no biological results entered. Moment analysis uses independent/common-moment inputs and Gaussian preactivation approximation with bounded parameter regions. Not universal self-normalization for arbitrary correlated architectures/weights, nor proof that all gradients can never vanish or explode. Only selected pages of102pagev1read.
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