no code implementations • 3 May 2021 • Boris Ruf, Marcin Detyniecki
To implement fair machine learning in a sustainable way, choosing the right fairness objective is key.
no code implementations • 9 Apr 2021 • Boris Ruf, Marcin Detyniecki
Most fair regression algorithms mitigate bias towards sensitive sub populations and therefore improve fairness at group level.
no code implementations • 16 Feb 2021 • Boris Ruf, Marcin Detyniecki
Fairness is a concept of justice.
no code implementations • 14 Sep 2020 • Boris Ruf, Marcin Detyniecki
The possible risk that AI systems could promote discrimination by reproducing and enforcing unwanted bias in data has been broadly discussed in research and society.
no code implementations • 15 Mar 2020 • Boris Ruf, Chaouki Boutharouite, Marcin Detyniecki
The potential risk of AI systems unintentionally embedding and reproducing bias has attracted the attention of machine learning practitioners and society at large.
1 code implementation • 13 Nov 2019 • Vincent Grari, Boris Ruf, Sylvain Lamprier, Marcin Detyniecki
The approach incorporates at each iteration the gradient of the neural network directly in the gradient tree boosting.
1 code implementation • 12 Nov 2019 • Vincent Grari, Boris Ruf, Sylvain Lamprier, Marcin Detyniecki
Second, by minimizing the HGR directly with an adversarial neural network architecture.
no code implementations • 10 Oct 2019 • Boris Ruf, Matteo Sammarco, Marcin Detyniecki
Towards conversational agents that are capable of handling more complex questions on contractual conditions, formalizing contract statements in a machine readable way is crucial.