Grégoire Montavon
3 papers in the PaperMetrix corpus
Papers by this author
-
Learning domain invariant representations by joint Wasserstein distance minimization
2023 · Neural Networks
Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of …
-
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
2022 · arXiv (Cornell University)
While the evaluation of explanations is an important step towards trustworthy models, it needs to be done carefully, and the employed metrics need to be well-understood. Specifically model randomization testing is often overestimated and regarded …
-
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
2022 · arXiv (Cornell University)
Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that …