Maximilian Alber

Learning how to explain neural networks: PatternNet and PatternAttribution

Pieter Jan Kindermans, Kristof T. Schütt, Maximilian Alber et al. · arXiv (Cornell University) · 2017 · 245 citations · Full text

Artificial Intelligence, Cognitive Science, Deep Neural Networks +14

The (Un)reliability of saliency methods

Pieter-Jan Kindermans, Sara Hooker, Julius Adebayo et al. · arXiv (Cornell University) · 2017 · 162 citations · Full text

Structured Prediction, Convolutional Neural Network, Engineering +18

Explanations can be manipulated and geometry is to blame

Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders et al. · arXiv (Cornell University) · 2019 · 145 citations · Full text

Artificial Intelligence, Cognitive Science, Engineering +13

Learning how to explain neural networks: PatternNet and PatternAttribution

Pieter-Jan Kindermans, Kristof T. Schütt, Maximilian Alber et al. · arXiv (Cornell University) · 2017 · 73 citations · Full text

Artificial Intelligence, Cognitive Science, Deep Neural Networks +14

Explanations can be manipulated and geometry is to blame

Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J. Anders et al. · Neural Information Processing Systems · 2019 · 54 citations

Artificial Intelligence, Cognitive Science, Engineering +13