Bias Amplification Dilemma
Yannic and Sara discuss the dilemma of investing resources in countering bias in models or revisiting the dataset to eliminate bias altogether. They explore how introducing sparsity can amplify bias and the challenges in redistributing bias within parametric models.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Sara Hooker - The Hardware Lottery, Sparsity and Fairness
Related Questions