Representing Human Ethical Requirements in Hybrid Machine Learning Models - Technical Opportunities and Fundamental Challenges

Aug 3, 2026

Upload by Aurora

Hybrid machine learning combines predefined rules with continual learning from data, enabling organizations to automate operations. Successful deployment depends on aligning implementations with human ethical requirements specified through laws, regulations, and standards. This study examines technical opportunities for representing such requirements in hybrid machine learning, comparing locally simple rules (e.g., road traffic regulations) with locally complex requirements (e.g., diagnosis procedures for functional disorders). Algebraic Machine Learning is used to represent these cases, highlighting both opportunities and fundamental limitations.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Abstract

Introduction

Hybrid machine learning and AI waves

This document is downloaded from the VTT’s Research Information Portal [https://cris.vtt.fi](https://cris.vtt.fi) VTT Technical Research Centre of Finland Representing Human Ethical Requirements in Hybrid Machine Learning Models Fox, Stephen; Rey, Vitor fortes Published in: Machine Learning and Knowledge Extraction DOI: 10.3390/make6010027 Published: 08/03/2024 Document Version Publisher's final version License CC BY Link to publication Please cite the original version: Fox, S. , & Rey, V. F. (2024) . Representing Human Ethical Requirements in Hybrid Machine Learning Models: Technical Opportunities and Fundamental Challenges. Machine Learning and Knowledge Extraction, 6(1), 580- 592. [https://doi.org/10.3390/make6010027](https://doi.org/10.3390/make6010027) VTT [http://www.vtt.fi](http://www.vtt.fi) [P.O. box 1000FI-02044 VTT](P.O. box 1000FI-02044 VTT)[ ](P.O. box 1000FI-02044 VTT)Finland By using VTT’s Research Information Portal you are bound by the following Terms & Conditions. I have read and I understand the following statement: This document is protected by copyright and other intellectual property rights, and duplication or sale of all or part of any of this document is not permitted, except duplication for research use or educational purposes in electronic or print form. You must obtain permission for any other use. Electronic or print copies may not be offered for sale. Download date: 04. Jun. 2024 machine learning & knowledge extraction Article Representing Human Ethical Requirements in Hybrid Machine Learning Models: Technical Opportunities and Fundamental Challenges Stephen Fox 1,* and Vitor Fortes Rey 2,3 Citation: Fox, S.; Rey, V.F. Representing Human Ethical Requirements in Hybrid Machine Learning Models: Technical Opportunities and Fundamental Challenges. Mach. Learn. Knowl. Extr. 2024, 6, 580–592. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/make6010027](10.3390/make6010027) Received: 11 December 2023 Revised: 16 February 2024 Accepted: 28 February 2024 Published: 8 March 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 VTT Technical Research Centre of Finland, 02150 Espoo, Finland 2 DFKI German Research Center for Artificial Intelligence, 67663 Kaiserslautern, Germany 3 RPTU University Kaiserslautern-Landau, 67663 Kaiserslautern, Germany; [fortes@dfki.uni-kl.de](fortes@dfki.uni-kl.de) * [Correspondence: stephen.fox@vtt.fi](Correspondence: stephen.fox@vtt.fi) Abstract: Hybrid machine learning encompasses predefinition of rules and ongoing learning from data. Human organizations can implement hybrid machine learning (HML) to automate some of their operations. Human organizations need to ensure that their HML implementations are aligned with human ethical requirements as defined in laws, regulations, standards, etc. The purpose of the study reported here was to investigate technical opportunities for representing human ethical requirements in HML. The study sought to represent two types of human ethical requirements in HML: locally simple and locally complex. The locally simple case is road traffic regulations. This can be considered to be a relatively simple case because human ethical requirements for road safety, such as stopping at red traffic lights, are defined clearly and have limited scope for personal interpretation. The locally complex case is diagnosis procedures for functional disorders, which can include medically unexplained symptoms. This case can be considered to be locally complex because human ethical requirements for functional disorder healthcare are less well defined and are more subject

FAQs

What is the focus of the study on hybrid machine learning?

The study investigates technical opportunities for representing human ethical requirements in hybrid machine learning models.

How does the paper distinguish locally simple versus locally complex ethical requirements?

Locally simple cases are clearly defined and limited in scope, exemplified by road traffic regulations. Locally complex cases are less well defined and more open to personal interpretation, exemplified by diagnosis procedures for functional disorders.

What do the findings suggest about representing ethical requirements?

They indicate technical opportunities due to the combination of top-down rules and bottom-up learning, but also identify limitations rooted in challenges of defining complex ethical requirements and the risk of opposing interpretations.

Aug 3, 2026

Upload by Aurora