An approximation theory perspective on machine learning

Neural Networks 2026 Open access

Read full text
Authors: H. N. Mhaskar, Efstratios Tsoukanis, Ameya D. Jagtap
DOI: 10.1016/j.neunet.2026.108841
Cited by: 3
References: 137

Abstract

are drawn from a finite set of values. We summarize another recent paper that establishes a deep connection between signal separation problems and classification problems, proposing that classification tasks should be approached as instances of signal separation. We conclude by identifying several open research problems that warrant further investigation.

Fields of Study & Subjects

Computability Logic AI Algorithms Gaussian Processes and Bayesian Inference Stochastic Gradient Optimization Techniques

Publication details

Journal / source
Neural Networks
Publisher
Elsevier BV
Volume
200
Pages
108841–108841
Publication date
13 March 2026
Language
EN