Our expertise in Interactive Machine Learning is represented by the Visual-Interactive Machine Learning group led by Dr. Jürgen Bernard. Particular research interests in concepts, techniques, and applications is conducted along the following three pillars:
Interactive Data Labeling techniques help to support the data labeling process in an effective and efficient way. Labeling is an important precondition for supervised Machine Learning tasks.
Interactive Similarity Search is the research for similarity functions for data objects or digital documents, performed in a visual-interactive and human-centered way.
Visual Analytics is one means to conduct Interactive Machine Learning. GRIS combines a broad set of competences reflected by supported data types, analysis techniques, and application areas.
Interactive Machine Learning explained
Interactive Machine Learning focuses on human-centered aspects of Machine Learning and the iterative Machine Learning process. Overall goal is to combine the strengths of humans and machines to leverage the Machine Learning process.