Abstract: Historical data used for supervised learning may contain discrimination. We study how to train classifiers on such data, so that they are discrimination free with respect to a given ...

Goffin’s cockatoos excel at basic weight sorting but struggle with more complex tasks requiring associating heavier/lighter ...

Fairness algorithms, a recent topic in machine learning, aims to avoid outcome decisions that are unfair to certain groups or individuals. In this project we implement two of such fairness algorithms, ...

Handling Conditional Discrimination: This paper argues that most fairness techniques aim to remove all discrimination and do not take into account the part of discrimination that may be explanable by ...

The American Journal of Psychology, Vol. 95, No. 4 (Winter, 1982), pp. 571-580 (10 pages) Pigeons learned a pair of two-choice conditional discriminations concurrently. One was red/green identity ...

Revised: This Reviewed Preprint has been revised by the authors in response to the previous round of peer review; the eLife assessment and the public reviews have been updated where necessary by the ...