AI Paper Spotlights - Extending Explainable Artificial Intelligence
Explainable artificial intelligence (XAI) is becoming more and more important for the applicability of AI, particularly in light of the coming EU AI Act. Yet, the interpretation of machine learning models can vary widely, depending on the data and the domain to which it is applied. This means, in many cases, a simple pixel-wise heat map is not sufficient to strengthen the intuition of an analyst. We aim to explore the complex structures that neural networks can learn from, especially when dealing with graph data.
🔎 About our speaker:
Thomas Schnake is a PhD student at the Technical University of Berlin and BIFOLD, with a background in mathematics (BSc & MSc) and scientific computing (MSc). His research focuses on developing explainable AI solutions tailored to specific applications, particularly in quantum chemistry and natural language processing. He is happy that I could publish on these topics a Journal paper at IEEE TPAMI and two ICML papers between 2021 and today.
#artificialintelligence #machinelearning