Technical University of Berlin, Fraunhofer Heinrich Hertz Institute, Germany
Concept-Level Explainable AI
The emerging field of Explainable AI (XAI) aims to bring transparency to today’s powerful but opaque deep learning models. This talk will present Concept Relevance Propagation (CRP), a next-generation XAI technique which explains individual predictions in terms of localized and human-understandable concepts. Other than the related state-of-the-art, CRP not only identifies the relevant input dimensions (e.g., pixels in an image) but also provides deep insights into the model’s representation and the reasoning process. This makes CRP a perfect tool for AI-supported knowledge discovery in the sciences. In the talk we will demonstrate on multiple datasets, model architectures and application domains, that CRP-based analyses allow one to (1) gain insights into the representation and composition of concepts in the model as well as quantitatively investigate their
role in prediction, (2) identify and counteract Clever Hans filters focusing on spurious correlations in the data, and (3) analyze whole concept subspaces and their contributions to fine-grained decision making. By lifting XAI to the concept level, CRP opens up a new way to analyze, debug and interact with ML models, which is of particular interest in safety-critical applications and the sciences.
Wojciech Samek is a professor in the Department of Electrical Engineering and Computer Science at the Technical University of Berlin and is jointly heading the Department of Artificial Intelligence at Fraunhofer Heinrich Hertz Institute (HHI), Berlin, Germany. He studied computer science at Humboldt University of Berlin, Heriot-Watt University and University of Edinburgh and received the Dr. rer. nat. degree with distinction (summa cum laude) from the Technical University of Berlin in 2014. During his studies he was awarded scholarships from the German Academic Scholarship Foundation and the DFG Research Training Group GRK 1589/1, and was a visiting researcher at NASA Ames Research Center, Mountain View, USA. Dr. Samek is associated faculty at the BIFOLD – Berlin Institute for the Foundation of Learning and Data, the ELLIS Unit Berlin, the DFG Research Unit DeSBi, and the DFG Graduate School BIOQIC, and member of the scientific advisory board of IDEAS NCBR – Polish Centre of Innovation in the Field of Artificial Intelligence. Furthermore, he is a senior editor of IEEE TNNLS, an editorial board member of Pattern Recognition, and an elected member of the IEEE MLSP Technical Committee and the Germany’s Platform for Artificial Intelligence. He is recipient of multiple best paper awards, including the 2020 Pattern Recognition Best Paper Award and the 2022 Digital Signal Processing Best Paper Prize, and part of the expert group developing the ISO/IEC MPEG-17 NNC standard. He is the leading editor of the Springer book “Explainable AI: Interpreting, Explaining and Visualizing Deep Learning” (2019), co-editor of the open access Springer book “xxAI – Beyond explainable AI” (2022), and organizer of various special sessions, workshops and tutorials on topics such as explainable AI, neural network compression, and federated learning. Dr. Samek has coauthored more than 150 peer-reviewed journal and conference papers; some of them listed as ESI Hot (top 0.1%) or Highly Cited Papers (top 1%)