120Compare SHAP and LIME for explaining model predictions. What does SHAP guarantee that LIME does not?▼mediumGoogleMicrosoftAmazon2 replies◆ premiumBoth explain one prediction by crediting features, but only one is backed by a uniqueness theorem. What interviewers reward is knowing SHAP's game-theory guarantees, LIME's instability, and when each fits. Here is the answer.Open full answer →
121Explain integrated gradients for attribution. Why use it over raw gradients, and how do you pick the baseline?▼hardGoogleGoogle DeepMindNVIDIA1 replies◆ premiumRaw gradient saliency maps are noisy and saturate. Integrated gradients cures both with two axioms and a path integral, yet the baseline choice quietly decides the answer. Here is what a careful candidate explains.Open full answer →
