• search hit 31 of 64
Back to Result List

Alternating Transfer Functions to Prevent Overfitting in Non-Linear Regression with Neural Networks

  • In nonlinear regression with machine learning methods, neural networks (NNs) are ideally suited due to their universal approximation property, which states that arbitrary nonlinear functions can thereby be approximated arbitrarily well. Unfortunately, this property also poses the problem that data points with measurement errors can be approximated too well and unknown parameter subspaces in the estimation can deviate far from the actual value (so-called overfitting). Various developed methods aim to reduce overfitting through modifications in several areas of the training. In this work, we pursue the question of how an NN behaves in training with respect to overfitting when linear and nonlinear transfer functions (TF) are alternated in different hidden layers (HL). The presented approach is applied to a generated dataset and contrasted to established methods from the literature, both individually and in combination. Comparable results are obtained, whereby the common use of purely nonlinear transfer functions proves to be not recommended generally.

Download full text files

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Philipp Seitz, Jan Schmitt
URN:urn:nbn:de:bvb:863-opus-49199
Persistent identifier:https://doi.org/10.1080/0952813X.2023.2270995
Parent Title (English):Journal of Experimental & Theoretical Artificial Intelligence
Document Type:Article
Language:English
Year of publication:2023
Publishing Institution:Technische Hochschule Würzburg-Schweinfurt
Release Date:2024/01/16
Tag:Machine learning; nonlinear regression; function approximation; overfitting; transfer function
Institutes and faculty:Institute / Institut Digital Engineering (IDEE)
Open access colour:Gold
Licence (German):License LogoCreative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International
Verstanden ✔
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.