Embargoed until:
2025-07-08

On the Role of Taylor’s Formula in Machine Learning

Abstract

The classical Taylor’s formula is an elementary tool in mathematical analysis and function approximation. Its role in the optimization theory, whose data-driven variants have a central role in machine learning training algorithms, is well-known. However, utilization of Taylor’s formula in the derivation of new machine learning methods is not common and the purpose of this article is to introduce such use cases. Both a feedforward neural network and a recently introduced distance-based method are used as data-driven models. We demonstrate and assess the proposed techniques empirically both in unsupervised and supervised learning scenarios.

Main Authors

Kärkkäinen, Tommi Neittaanmäki, Pekka Rantalainen, Marja-Leena

Format

Books Book part

Published

2023

Series

Computational Methods in Applied Sciences

Subjects

Taylor’s formula

machine learning

neural networks

distance-based methods

neuroverkot

koneoppiminen

Publication in research information system

https://converis.jyu.fi/converis/portal/detail/Publication/183935626

Publisher

Springer

The permanent address of the publication

https://urn.fi/URN:NBN:fi:jyu-202402141863Käytä tätä linkitykseen.

Parent publication ISBN

978-3-031-29081-7

Review status

Peer reviewed

ISSN

1871-3033

DOI

https://doi.org/10.1007/978-3-031-29082-4_16

Language

English

Published in

Computational Methods in Applied Sciences

Is part of publication

Impact of Scientific Computing on Science and Society

Citation

Kärkkäinen, T. (2023). On the Role of Taylor’s Formula in Machine Learning. In P. Neittaanmäki, & M.-L. Rantalainen (Eds.), Impact of Scientific Computing on Science and Society (pp. 275-294). Springer. Computational Methods in Applied Sciences, 58. https://doi.org/10.1007/978-3-031-29082-4_16

License