Uncovering Data Bias
Sara discusses the challenges of labeling data and protected attributes, proposing unsupervised methods to identify biased data subsets for further auditing. Tim delves into the complexities of interpretability in deep learning models, questioning the trade-offs between model complexity and understandability.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Sara Hooker - The Hardware Lottery, Sparsity and Fairness
Related Questions