Interactive Machine Learning

Interactive Machine Learning (IML) is the design and implementation of algorithms and intelligent user interface frameworks that facilitate machine learning with the help of human interaction. We want computers to learn from humans by interacting with them in natural language and by observing them. Humans can also teach computers.

Our goal is to improve the interaction between humans and machines to update ML models, by leveraging both state-of-the-art human-computer-interaction and machine learning approaches. Basic and fundamental research reveals deep insights into users' behaviours, needs, and goals. We try to think more deeply, and machine learning should become accessible to millions of end users.

Be ambitious: we can “assist” AI systems in becoming self-sustaining, “lifelong” learners. This includes to (1) develop insights into the importance of the social and cultural contexts of machine learning; (2) create machine learning systems that actively seek information; (3) realise the need to pay attention to the incomplete context understandings and naive generalisations that machine learning systems, in particular end-to-end systems, bring with them to a given subject. We keep our eyes focussed on these fundamental questions and develop multimodal multisensor interfaces for robust machine learning, thereby including eye tracking, digital pens, image recognition, and speech dialogue for example.

Student projects (PhD, master, bachelor) are important to us, recent projects can be found here: iml.dfki.de.

Application areas of our Applied AI group include medicine (ai-in-medicine.dfki.de) and industrial AI / Industry 4.0 (https://smartfactories.dfki.de). We are also engaged in Computational Sustainability & Technology (https://cst.dfki.de/).

Special AI transfer topics and challenges: explainability (XAI), transparency, fairness, robustness, machine teaching, human-centred design, information extraction (IE) and natural language processing (NLP), semantic web, common sense modelling, hybrid cognitive technologies, context-based interpretation, robustness and trustworthy AI, hybrid teams, human-robot interaction (HRI), learning with small datasets, transfer learning, interactive deep learning, never ending learning, AI and Art, metacognition and introspection