This graduate course follows a research-based teaching approach and discusses methods for combining human intelligence with machine learning to solve problems from health informatics. For practical applications we focus on Python. Students should get acquainted with the specific features of medical data and basic examples of automatic and interactive machine learning, also being able to use specific programming languages for programming various typical project exercises.
ML meets health informatics, introduction to the health domain, challenges and future direction; fundamentals and specifics of biomedical data, information and knowledge; knowledge, decision, cognition, reasoning, probability, uncertainty, Bayesian statistics, Gaussian processes; aML - Applied Machine Learning, deep learning on biomedical images, with practical exercises using Berkeley Caffe; aML: text document classification in Python; iML - Interactive Machine Learning: protein folding, crowdsourcing, gamification and ML; iML: towards open medical data: k-anonymization, privacy preserving ML; iML: intelligent, interactive visualization and visual analytics, subspace clustering; iML: interactive tumor growth simulation; outlook and future challenges.
ECTS-Breakdown (Summe=75h, entspricht 3 ECTS):
15h: Anwesenheit in der Vorlesung
15h: Vor- und Nachbereitung der Vorlesung
30h: Ausarbeitung und Präsentation des Projekts
15h: Prüfung inklusive Vorbereitung
will be adapted to the previous knowledge of the students and announced once the course has started
paper based on selected project (40%)
presentation of selected project (30%)
final written exam (30%)
Holzinger, A. 2016. Interactive Machine Learning (iML). Informatik Spektrum, 39, (1), 64-68, doi:10.1007/s00287-015-0941-6.