Operator theory, kernels, and Feedforward Neural Networks

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

doi:10.48550/arxiv.2301.01327

Back

Operator theory, kernels, and Feedforward Neural Networks

Preprint

Open access

Operator theory, kernels, and Feedforward Neural Networks

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

ArXiv.org

01/03/2023

DOI: 10.48550/arxiv.2301.01327

Files and links (1)

url

https://doi.org/10.48550/arxiv.2301.01327View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

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.

Details

Title: Subtitle: Operator theory, kernels, and Feedforward Neural Networks
Creators: Palle E. T Jorgensen
Myung-Sin Song
James Tian
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.2301.01327
ISSN: 2331-8422
Language: English
Date posted: 01/03/2023
Academic Unit: Mathematics
Record Identifier: 9984357456902771

Metrics

66 Record Views