Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Is it ethical to avoid error analysis?
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science and Engineering.ORCID iD: 0000-0003-4973-9255
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science and Engineering.ORCID iD: 0000-0002-0535-1761
2017 (English)Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Machine learning algorithms tend to create more accurate models with the availability of large datasets. In some cases, highly accurate models can hide the presence of bias in the data. There are several studies published that tackle the development of discriminatory-aware machine learning algorithms. We center on the further evaluation of machine learning models by doing error analysis, to understand under what conditions the model is not working as expected. We focus on the ethical implications of avoiding error analysis, from a falsification of results and discrimination perspective. Finally, we show different ways to approach error analysis in non-interpretable machine learning algorithms such as deep learning.

Place, publisher, year, edition, pages
arXiv , 2017.
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-15534OAI: oai:DiVA.org:bth-15534DiVA, id: diva2:1159328
Conference
2017 Workshop on Fairness, Accountability, and Transparency in Machine Learning (FAT/ML 2017), Halifax, Canada
Funder
Knowledge Foundation, 20170032
Available from: 2017-11-22 Created: 2017-11-22 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

fulltext(80 kB)151 downloads
File information
File name FULLTEXT01.pdfFile size 80 kBChecksum SHA-512
ab0d69a2f002e606000f132f617f67b05735956e60b3e5c0bf188051d42bdc8b254b89346b1317c023fa339ddc3a21e327f74f5c51161fb7415f1f96d85af4ec
Type fulltextMimetype application/pdf

Other links

https://arxiv.org/abs/1706.10237

Search in DiVA

By author/editor
García Martín, EvaLavesson, Niklas
By organisation
Department of Computer Science and Engineering
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 151 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 138 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf