Operator theory, kernels, and feedforward neural networks: Operator theory, kernels, and feedforward neural networks

Palle E. T. Jorgensen; Myung-Sin Song; James Tian

doi:10.1007/s11785-025-01802-7

Back

Operator theory, kernels, and feedforward neural networks: Operator theory, kernels, and feedforward neural networks

Journal article

Peer reviewed

Operator theory, kernels, and feedforward neural networks: Operator theory, kernels, and feedforward neural networks

Palle E. T. Jorgensen, Myung-Sin Song and James Tian

Complex analysis and operator theory, Vol.19(7), 179

09/11/2025

DOI: 10.1007/s11785-025-01802-7

View Online

Abstract

In this paper we show how specific families of positive definite kernels serve as powerful tools in analyses of iteration algorithms for multiple layer feedforward Neural Network models. Our focus is on particular kernels that adapt well to learning algorithms for data-sets/features which display intrinsic self-similarities at feedforward iterations of scaling.

Mathematics

Analysis

Article

General

Mathematics and Statistics

Operator Theory

Details

Title: Subtitle: Operator theory, kernels, and feedforward neural networks: Operator theory, kernels, and feedforward neural networks
Creators: Palle E. T. Jorgensen - University of Iowa
Myung-Sin Song - Southern Illinois University Edwardsville
James Tian - Mathematical Reviews
Resource Type: Journal article
Publication Details: Complex analysis and operator theory, Vol.19(7), 179
DOI: 10.1007/s11785-025-01802-7
ISSN: 1661-8254
eISSN: 1661-8262
Publisher: Springer International Publishing
Language: English
Date published: 09/11/2025
Academic Unit: Mathematics
Record Identifier: 9984962544002771

Metrics

2 Record Views