Software Demo @ BVM-Workshop: Interactive Visualization of 3D CNN Relevance Maps to Aid Model Comprehensibility

At this year's German Workshop on Image Processing in Medical Imaging (Bildverarbeitung für die Medizin, BVM), Martin presented is interactive relevance map visualization app to the research community. As a…

Continue ReadingSoftware Demo @ BVM-Workshop: Interactive Visualization of 3D CNN Relevance Maps to Aid Model Comprehensibility

DFG funding for a neural network system architecture to generate diagnostic explanations

I am happy to announce that the German Research Foundation (DFG) selected my project proposal “Towards a neural network system architecture for multimodal explanations” for funding. (DFG FKZ DY 151/2-1, Project No. 454834942) (more…)

Continue ReadingDFG funding for a neural network system architecture to generate diagnostic explanations

AAIC talk: Deep learning models for generating diagnostic explanations

In July 2020, I chaired the symposium “Doctor AI: Making computers explain their decisions” at the Alzheimer’s Association International Conference (AAIC). There, next to me, three internationally leading researchers in the field of Alzheimer’s disease and MRI data analysis with machine learning and neural networks presented their exciting talks (more…)

Continue ReadingAAIC talk: Deep learning models for generating diagnostic explanations