A3 Book section, Chapters in research books
On the Role of Taylor’s Formula in Machine Learning (2023)

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

JYU authors or editors

Publication details

All authors or editors: Kärkkäinen, Tommi

Parent publication: Impact of Scientific Computing on Science and Society

Parent publication editors: Neittaanmäki, Pekka; Rantalainen, Marja-Leena

ISBN: 978-3-031-29081-7

eISBN: 978-3-031-29082-4

Journal or series: Computational Methods in Applied Sciences

ISSN: 1871-3033

eISSN: 2543-0203

Publication year: 2023

Number in series: 58

Pages range: 275-294

Number of pages in the book: 450

Publisher: Springer

Place of Publication: Cham

Publication country: Switzerland

Publication language: English

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

Publication open access: Not open

Publication channel open access: 

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/93383

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.

Keywords: machine learning; neural networks (information technology)

Free keywords: Taylor’s formula; machine learning; neural networks; distance-based methods

Contributing organizations

Related projects

Ministry reporting: Yes

VIRTA submission year: 2023

Preliminary JUFO rating: 1