5 citations · 10 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022★ 4 cited
Evaluating the Impact of Loss Function Variation in Deep Learning for Classification
Simon Dräger, Jannik Dunkelau
The loss function is arguably among the most important hyperparameters for a neural network. Many loss functions have been designed to date, making a correct choice nontrivial. How…
cs.LG2022★ 5 cited
Towards Equalised Odds as Fairness Metric in Academic Performance Prediction
Jannik Dunkelau, Manh Khoi Duong
The literature for fairness-aware machine learning knows a plethora of different fairness notions. It is however wellknown, that it is impossible to satisfy all of them, as certain…