Banner Banner

Explaining Deep Neural Networks

Icon

Lead
Prof. Dr. Grégoire Montavon

Icon

Dept. of Mathematics and Computer Science, Institute for Computer Science
Arnimallee 7, 14195 Berlin

Explainable AI (XAI), Trustworthy and autonomous machine learning models, Deep neural networks

 

The Junior Research Group of Prof. Dr. Grégoire Montavon advances the foundations and algorithms of explainable AI (XAI) in the context of deep neural networks. One particular focus is on closing the gap between existing XAI methods and practical desiderata. Examples include using XAI to build more trustworthy and autonomous machine learning models and using XAI to model the behavior of complex real-world systems so that the latter become meaningfully actionable. In future research, the team explores: (1) how to use XAI to assess, on which data a deep neural network model can be trusted to perform autonomously or requires human intervention, and (2) how to use XAI in combination with a deep neural network to model complex real-world systems and identify actionable components. Grégoire Montavon and his team will collaborate with the members of BIFOLD’s “Explainable Artificial Intelligence Lab” (XAI-Lab).

Pattarawat Chormai, Jan Herrmann, Klaus-Robert Müller, Gregoire Montavon

Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces

December 30 , 2022
https://arxiv.org/abs/2212.14855

Philipp Keyl, Philip Bischoff, Gabriel Dernbach, Michael Bockmayr, Rebecca Fritz, David Horst, Nils Blüthgen, Gregoire Montavon, Klaus-Robert Müller, Frederick Klauschen

Single-cell gene regulatory network prediction by explainable AI

January 01 , 2023
https://academic.oup.com/nar/article/51/4/e20/6984592

Alexander Binder, Leander Weber, Sebastian Lapuschkin, Gregoire Montavon, Klaus-Robert Müller, Wojciech Samek

Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations

November 22 , 2022
https://arxiv.org/abs/2211.12486

Philipp Keyl, Michael Bockmayr, Daniel Heim, Gabriel Dernbach, Gregoire Montavon, Klaus-Robert Müller, Frederick Klauschen

Patient-level proteomic network prediction by explainable artificial intelligence

June 07 , 2022
https://www.nature.com/articles/s41698-022-00278-4

Prof. Dr. Grégoire Montavon

Research Group Lead

Lorenz Linhardt

Doctoral Researcher