Interactive Machine Learning

With the convergence of Artificial intelligence (AI), and Machine Learning (ML), Interactive Machine Learning (IML) is where the Human-Computer Interaction (HCI) community meets the ML community, with contributions from related fields such as cognitive science, computer graphics, design or the arts, and natural language processing, data mining, knowledge representation and reasoning. Our focus is to improve the interaction between humans and machines, by leveraging both more traditional HCI approaches, as well as solutions that involve state-of-the-art ML techniques.


Fairness, accountability, and transparency in machine learning, causation:
– Mitigate bias in machine learning
– Evaluate machine learning models
– Render ML models more interpretable
– How can we develop interpretable machine learning methods that provide ways to manage the complexity of a model and/or generate meaningful explanations?

Human interpretability in machine learning:
– Interpretation of black-box models (including deep neural networks)
– Causality of predictive models
– Visual analytics

Interpretable & reasonable deep learning and its applications:
– Analysis and comparison of methods to interpret & visualize deep learning models

Explainable artificial intelligence:
– Medical decision making
– Reliance on learned models in deployed applications
– What types of user interactions should be supported? How should explanation quality be measured?

Mixed initiative interaction:
The algorithm and the domain expert engage in a two-way dialogue to facilitate more accurate learning from less data compared to the classical approach of passively observing labeled data.
– Crowdsourcing
– Reinforcement learning
– Incremental learning
– Integral / one-shot learning
– Online learning

IML tools for enhancing human cognitive capabilities:
– Channeling human creativity, inventiveness and intuition
– Empower humans to make important decisions in a more informed way
– Help understand and foresee long-term implications of ML


Ongoing Research Projects

Facetted Search

As medical records may cover a very long history of diseases (up to 30 years) and include a vast number of diagnoses, symptoms, results, medications, and laboratory values, we could highly benefit from advanced search Read more…


Handwriting Spellchecker

In comparison to typing, handwriting stimulates different parts of the human brain and brings into play a very different cognitive process. Many of today’s tasks benefit from digitalization and digitization of handwriting input and with Read more…


Multi-Sketch Recognition

Many of todays processes benefits from digitization and digitalization of written content when it comes to data aquisition for machine learning tasks. Through the use of state of the art handwriting and gesture recognition we Read more…



In Kognit (2014–2015), we enter the mixed reality realm for helping dementia patients. Dementia is a general term for a decline in mental ability severe enough to interfere with daily life. Memory loss is an Read more…

Interactive Machine Learning Group

German Research Center for Artificial Intelligence (DFKI)


German Research Center for Artificial Intelligence
Stuhlsatzenhausweg 3
Saarland Informatics Campus, Geb. D 3_2
D-66123 Saarbrücken

Contact Us