Operator theory, kernels, and Feedforward Neural Networks
Machine Learning
2023-01-09 v2 Functional Analysis
Operator Algebras
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.
Cite
@article{arxiv.2301.01327,
title = {Operator theory, kernels, and Feedforward Neural Networks},
author = {Palle E. T. Jorgensen and Myung-Sin Song and James Tian},
journal= {arXiv preprint arXiv:2301.01327},
year = {2023}
}
Comments
23 pages