On 4.11.2019 we started our FWF project P-32 554-N “explainable AI”, with the first doctoral student in explainable-AI, Dipl.-Ing. Anna SARANTI and the Master student Simon STREIT. We are just setting up and enlarging the group, so this exciting project will be a great opportunity for interested Bachelor, Master and PhD students and we are happy to contribute to the international ai/machine learning research community. All outcomes of this project, algorithms and tools, will be made openly available to the international AI/machine learning research community.
Background: The progress of statistical machine learning methods has made Artificial Intelligence (AI) increasingly successful. Deep learning even exceed human performance in many domains. However, their full potential is limited by the difficulty to generate the underlying explanatory structures. The central problem is that they are regarded as opaque ”black-boxes” and even if we understand the mathematical principles, they lack an explicit declarative knowledge representation. This calls for tools enabling to make decisions transparent, understandable and explainable. A huge motivation for this project are rising legal and privacy issues, which make ”black-boxes” difficult to use. This does not imply a ban on automatic learning approaches or an obligation to explain everything all the time, however, there must be a possibility to make the results re-traceable on demand. The topic of this project is explainability and our goal is to make existing AI/ML algorithms transparent, retraceable, thus understandable to a medical professional and outline a possible new approach towards explainable AI. We learned of a variety of technical solutions which are currently in development, which could help explain AI/ML systems and their decisions. Transparent algorithms could appropriately enhance trust of medical professionals, thereby raising acceptance of machine learning solutions specifically and of AI generally. The KANDINSKY-Patterns, our Swiss-Knife for the study of explainableai will be a great help for this project: