Reference library
Approximation by superpositions of a sigmoidal function
Paper summary
Proves that finite sums of affine inputs passed through suitable sigmoidal functions can approximate continuous functions on a compact domain. The theorem establishes representational capacity of a single-hidden-layer feedforward architecture.
Relevance to the project
Supports using a simple neural mechanism network to represent candidate F or updater functions. Width, optimization, stability, and GPU cost still require independent choices.
Existence of an approximation is not a method for finding it.
Source record
- Reference ID
- pdf-https-papers-baulab-info-papers-cybenko-1989-pdf
- Archived version
- Direct PDF cited in project notes; publication status needs source-specific inspection
- Summary provenance
- reference-library/papers/pdf-https-papers-baulab-info-papers-cybenko-1989-pdf/metadata.json · summary
- Review status
- initial orientation summary; not a critical full-paper review
- Reading scope
- Selected abstract/opening and available closing discussion/conclusion passages in the preserved text extract; broader project notes provide context. No reproduction of experiments, exhaustive methods review, or equation/figure audit.