Towards a Fairness Score for Machine Learning Training Data

Kurpicz-Briki, Mascha (January 2020). Towards a Fairness Score for Machine Learning Training Data (Unpublished). In: Applied Machine Learning Days Lausanne 2020. Lausanne. 25-29.01.2020.

Text AMLD2020_Poster.pdf Restricted to registered users only Download (4MB)

Digital ethics has become a more and more important topic, and is highly relevant also when it comes to machine learning. Biased training data (e.g. gender, racial bias, and more) can have dramatic consequences for the fairness of applications using machine learning models. When a model trained on biased data is used for smart decision making, unfair decisions might be taken. We therefore need a transparent and independent classification system, to measure the fairness of training data fed into machine learning algorithms.

Item Type:	Conference or Workshop Item (Poster)
Division/Institute:	School of Engineering and Computer Science > Institute for Data Applications and Security (IDAS) School of Engineering and Computer Science
Name:	Kurpicz-Briki, Mascha
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Language:	English
Submitter:	Mascha Kurpicz-Briki
Date Deposited:	07 Jul 2020 13:19
Last Modified:	07 Jul 2020 13:19
ARBOR DOI:	10.24451/arbor.11924
URI:	https://arbor.bfh.ch/id/eprint/11924