COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
Fairness in AIAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Elre Oldewage. Applications of machine learning almost always involve data about people. Unfortunately, training data for such applications usually encode the demographic disparities that are present (or have historically been present) in our society. This, in turn, may lead to machine learning solutions that re-enforce discrimination—not necessarily on purpose, but due to bias in the training data. As machine learning researchers, the solution may seem simple: get better, unbiased data. However, as we will discuss, bias is nigh impossible to escape completely. Instead, we must develop techniques to identify and counter biased decision-making by ML models. In this talk, we will provide motivational examples and discuss a number of sources from which bias and discrimination may arise. We will consider different definitions for fairness, eventually boiling them down to three main criteria: independence, separation and sufficiency. We’ll also discuss a number of bias mitigation strategies, by which these criteria may be achieved. Finally, we’ll discuss the limitations of the three observational criteria and briefly discuss fairness from a causal perspective. Recommended reading: Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., and Galstyan, A. A Survey on Bias and Fairness in Machine Learning. arXiv e-prints, art. arXiv:1908.09635, 2019. Available at: https://arxiv.org/abs/1908.09635 Additional reading, for those interested in the topic, is the Fair ML Book, available for free online: Barocas, S., Hardt, M., and Narayanan, A. Fairness and Machine Learning. fairmlbook.org, 2019. Available at: http://www.fairmlbook.org This talk is part of the Machine Learning Reading Group @ CUED series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsAre there too may people? A head-to-head debate on overpopulation cambridge centre for climate science Cambridge Indonesia AssociationOther talksCharges and Dipoles in Periodic Systems: Here Be Dragons Distribution-Free, Risk-Controlling Prediction Sets Language change in bilingual returnee children: mutual effects of bilingual experience and cognition Improving EDI in academic and field settings How we know what not to think (3pm start) |