The Holzinger Group is working at the intersection of artificial intelligence (AI) and machine learning (ML) and promotes a synergetic approach of a human-centered AI to augment human intelligence with machine intelligence. The groups main focus is on explainable AI and interpretable machine learning, particularly in interactive machine learning (iML) with a human-in-the-loop. Our main application domain is medicine and health. We work on contributions to the international research community, so that a human expert can understand the underlying explanatory factors of data driven AI results – towards causality. This answers the question of why an AI decision has been made and enables ethical responsible and trustful AI and transparent, verifiable machine learning. This is highly relevant for human health, for research, business and industry.

Ultimately, to reach a level of usable computational intelligence, we need

  1. to learn from prior data,
  2. to extract knowledge,
  3. to generalize – i.e. guessing where probability mass/density concentrates,
  4. to fight the curse of dimensionality, and
  5. to disentangle underlying explanatory factors of the data – i.e. sensemaking in the context of an application domain.

Consequently, interactive machine learning (iML) with a human-in-the-loop, thereby making use of human cognitive abilities, can be of particular interest to solve problems, where learning algorithms suffer due to insufficient training samples, dealing with complex data and/or rare events or computationally hard problems, e.g. subspace clustering, protein folding, or k-anonymization. Here human experience and knowledge can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem reduces greatly in complexity through the input and the assistance of a human agent involved in the learning phase.

We work consistently on a synergistic combination of methods, techiques and approaches which offer ideal conditions to support human intelligence with computational intelligence: Human–Computer Interaction (HCI) and Knowledge Discovery & Data Mining (KDD).

Successful Machine Learning & Knowledge Extraction (MAKE) pipelines require a concerted effort of integrative research across seven fields:

1) DATA – data fusion, preprocessing, mapping, knowledge representation, environments, etc.
2) LEARNING – algorithms, contextual adaptation, causal reasoning, transfer learning, etc.
3) VISUALIZATION – intelligent interfaces, human-AI interaction, dialogue systems, explanation interfaces, etc.
4) PRIVACY – data protection, safety, security, reliability, verifiability, trust, ethics and social issues, etc.
5) NETWORK – graphical models, graph-based machine learning, Bayesian inference, etc.
6) TOPOLOGY – geometrical machine learning, topological and manifold learning, etc.
7) ENTROPY – time and machine learning, entropy-based learning, etc.

Visit the CD-MAKE conference.