Challenges of biomedicine, health and the life sciences and the chances of Interactive Machine Learning for Knowledge Discovery

In this presentation I will provide an overview of the variations and complexity of data sets from biomedicine, health care and the life sciences and the problems and challenges biomedical researchers of today are faced, when trying to gain insight into their data to discover unknown unknowns. Machine learning algorithms may be of help here, and a best practice today is demonstrated by autonomous vehicles ("Google car"). However, in complex domains such as biomedicine, where we deal with uncertain, probabilistic, and weakly structured data the application of fully automatic machine learning algorithms endangers the modelling of artifacts. Therefore I will emphasize in my presentation the importance of supporting human intelligence with interactive 1 of 10 machine learning by putting the human-in-the-loop. Our long term goal is to contribute towards cognitive computing systems, that learn and interact naturally with experts together to extend what neither a human nor a computer could do on its own. ; Non UBC ; Unreviewed ; Author affiliation: Medical University Graz ; Faculty