Work

Approximation by non-symmetric networks for cross-domain learning

Year: 2025

Type: article

Abstract: networks when r is not necessarily an integer. Our general results apply to the approximation of functions with small smoothness compared to the dimension of the input space.

Source: Neural Networks

DOI: 10.1016/j.neunet.2025.107282

Author: H.N. Mhaskar

Institution: Claremont Graduate University

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $3,110

Funders: National Science Foundation, Directorate for Mathematical and Physical Sciences, Office of Naval Research

Awards: Collaborative Research: Computational Harmonic Analysis Approach to Active Learning, G22410596, G5381193549, G580337505

OpenAlex ID: W4407857900

FWCI: 0.408

Cites: 49

Cited by: 1

Related to: 10