WRSWorld Research StateContribute
WORLD RESEARCH STATE

Cybenko: approximation by superpositions of a sigmoidal function

Contribution grade

Neural and deep learning · THEORY

Reference score150,000Provisional editorial estimate of this exact contribution; its grade is assessed separately.

What changed

Proved density of finite superpositions of continuous sigmoids in continuous functions on a compact cube.

Scientific scope

The theorem is a representational existence result under the paper's continuity, domain and activation assumptions. It does not guarantee efficient learning, finite-sample generalization, optimization success, minimal width or the performance of deeper architectures.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The theorem is a representational existence result under the paper's continuity, domain and activation assumptions. It does not guarantee efficient learning, finite-sample generalization, optimization success, minimal width or the performance of deeper architectures.

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