A method for evaluation of learning components

DSpace Repository

A method for evaluation of learning components

Show full item record

Files for download

Authors version of ...

Simple item record

Publication Article, peer reviewed scientific
Title A method for evaluation of learning components
Author(s) Lavesson, Niklas ; Boeva, Veselka ; Tsiporkova, Elena ; Davidsson, Paul
Date 2014
English abstract
Today, it is common to include machine learning components in software products. These components offer specific functionalities such as image recognition, time series analysis, and forecasting but may not satisfy the non-functional constraints of the software products. It is difficult to identify suitable learning algorithms for a particular task and software product because the non-functional requirements of the product affect algorithm suitability. A particular suitability evaluation may thus require the assessment of multiple criteria to analyse trade-offs between functional and non-functional requirements. For this purpose, we present a method for APPlication-Oriented Validation and Evaluation (APPrOVE). This method comprises four sequential steps that address the stated evaluation problem. The method provides a common ground for different stakeholders and enables a multi-expert and multi-criteria evaluation of machine learning algorithms prior to inclusion in software products. Essentially, the problem addressed in this article concerns how to choose the appropriate machine learning component for a particular software product.
DOI http://dx.doi.org/10.1007/s10515-013-0123-1 (link to publisher's fulltext)
Link http://link.springer.com/article/10.1007%2Fs10515-013-0123-1 (external link to publication)
Publisher Springer
Host/Issue Automated Software Engineering;1
Volume 21
ISSN 0928-8910
Pages 41-63
Language eng (iso)
Subject(s) macine learning
software components
Research Subject Categories::TECHNOLOGY
Handle http://hdl.handle.net/2043/15264 (link to this page)

This item appears in the following Collection(s)

Show full item record



My Account