Towards A Rigorous Science of Interpretable Machine Learning

Finale Doshi‐Velez, Been Kim

arXiv (Cornell University)

Artificial IntelligenceRigorous EvaluationInterpretable Machine LearningRigorous ScienceEngineering +10

SmoothGrad: removing noise by adding noise

Daniel Smilkov, Nikhil Thorat, Been Kim, +2

arXiv (Cornell University)

Geometric LearningConvolutional Neural NetworkEngineeringMachine LearningImage Classifier +18

Interpretability Beyond Feature Attribution: Quantitative Testing with\n Concept Activation Vectors (TCAV)

Been Kim, Martin Wattenberg, Justin Gilmer, +4

arXiv (Cornell University)

Sanity Checks for Saliency Maps

Julius Adebayo, Justin Gilmer, Michael Muelly, +3

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningSanity ChecksAttention +20

Examples are not enough, learn to criticize! Criticism for Interpretability

Been Kim, Rajiv Khanna, Oluwasanmi Koyejo

Neural Information Processing Systems

Artificial IntelligenceEngineeringMachine LearningSemanticsNearest Prototype Classifier +16

Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Been Kim, Martin Wattenberg, Justin Gilmer, +4

arXiv (Cornell University)

Concept FormationConvolutional Neural NetworkEngineeringMachine LearningObject Categorization +25

A Benchmark for Interpretability Methods in Deep Neural Networks

Sara Hooker, Dumitru Erhan, Pieter-Jan Kindermans, +1

arXiv (Cornell University)

Convolutional Neural NetworkApproximate AccuracyMachine LearningEngineeringMachine Learning Tool +15

Human-Centered Tools for Coping with Imperfect Algorithms During Medical Decision-Making

Carrie J. Cai, Emily Reif, Narayan Hegde, +8

Artificial IntelligenceEngineeringMachine LearningClinical Decision-makingHuman-centered Tools +25

Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments

Xiao Bai, Xiang Wang, Xianglong Liu, +4

Pattern Recognition

Artificial IntelligenceConvolutional Neural NetworkMachine VisionMachine LearningData Science +10

Learning how to explain neural networks: PatternNet and PatternAttribution

Pieter Jan Kindermans, Kristof T. Schütt, Maximilian Alber, +4

arXiv (Cornell University)

Artificial IntelligenceCognitive ScienceDeep Neural NetworksMachine LearningData Science +12