Berlin Institute for the Foundations of Learning and Data

Duration: July 2018 – present

BIFOLD research groups conduct fundamental research on a wide range of topics concerning foundations and methods of Artificial Intelligence (AI). This includes the management and processing of distributed and Big Data. As Machine Learning (ML) is one of the main fields for modern AI and the new wave of AI applications, we also focus on a variety of Machine Learning methods such as reinforced and Bayesian Machine Learning as well as unsupervised and recurrent Deep Learning.

Project partners:

TU Berlin, HU Berlin, FU Berlin, Charité, Uni Potsdam, Uni Braunschweig, Fraunhofer FOKUS, DFKI, Zuse Institute, WIAS, MDC, HPI, MPI


C. J. Anders, L. Weber, D. Neumannc, W. Samek, K.-R. Müller, S. Lapuschkin. Finding and removing Clever Hans: Using explanation methods to debug and improve deep models. Information Fusion. 2022.

W. Samek, G. Montavon, S. Lapuschkin, C. J. Anders, K.-R. Müller. Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications. Proceedings of the IEEE, vol. 109, no. 3, pp. 247-278, March 2021.

L. Ruff, J. R. Kauffmann, R. A. Vandermeulen, G. Montavon, W. Samek, M. Kloft, T. G. Dietterich, K.-R. Müller. A Unifying Review of Deep and Shallow Anomaly Detection. Proceedings of the IEEE, 2021.

S.-K. Yeom, P. Seegerer, S. Lapuschkin, A. Binder, S. Wiedemann, K.-R. Müller, W. Samek. Pruning by explaining: A novel criterion for deep neural network pruning. Pattern Recognition. 2021.

J. Sun, S. Lapuschkin, W. Samek, A. Binder. Explain and improve: LRP-inference fine-tuning for image captioning models. Information Fusion. 2022.