PinnedKlas LeinoinTowards Data ScienceAI Explainability Requires RobustnessHow robustness to adversarial input perturbations affects model interpretabilityDec 7, 20211Dec 7, 20211
PinnedKlas LeinoinTowards Data ScienceTraining Provably-Robust Neural NetworksDefending against adversarial examples with GloRo NetsNov 13, 2021Nov 13, 2021
PinnedKlas LeinoinTowards Data ScienceOverfitting and Conceptual SoundnessHow feature usage informs our understanding of overfitting in deep networksOct 21, 2021Oct 21, 2021
Klas LeinoinTruLensOverfitting and Conceptual Soundness in Neural Network ModelsHow feature usage informs our understanding of overfitting in deep networksNov 4, 2021Nov 4, 2021
Klas LeinoinTruLensA Hands-on Introduction to Explaining Neural Networks with TruLensTransparency and Attribution MethodsAug 10, 20211Aug 10, 20211
