HPI Digital Health Cluster

Applied Machine Learning for Digital Health

General Information

You are viewing an archived version of the course, please find a newer version here

  • Teaching staff: Florian Borchert, Orhan Konak, Dr.-Ing. Matthieu-P. Schapranow
  • Location: Online seminar (phone confefence + screen sharing) -- please see below for dial-in instructions
  • 4 Semesterwochenstunden (SWS) 6 ECTS (graded)
  • Limit: Max. number of participants defined by the number of provided topics.
  • Moodle: AML4DH
  • Dates & times:
    • Wednesdays 1.30pm, and
    • Thursdays 9.15am.
  • First course: Wed Apr 22, 2020 at 01.30pm

Instructions to join the online semiar:

Please test the tool once before the first course in case you need to install a plugin or configure your local browser. Do not hesitate to contact anyone of us in advance, if you have any questions or encounter any issues when joining the seminar.


  • Due to the global spread of COVID19 (latest news), a university wide non-presence mode was announced by our chancellor. Therefore, we provide remote dial-in details for all meetings and consultation of the giving seminar to protect your health. Please help to flattern the curve by staying home and protect your health!
  • Topics and selection procedure will be presented during the kickoff event.


  • A. Transfer Learning with Synthetically Generated Data
  • B. Unsupervised Learning for Human Activity Recognition
  • C. Nurse Care Activity Recognition
  • D. Sensor Data Augmentation with GANs
  • E. Evaluation of Word Representations for German Medical Text
  • F. Creating High-quality Annotated Datasets for Medical Natural Language Processing
  • G. Weak Supervision for Medical Entity Extraction using the HUNER Dataset
  • H. Weak Supervision for Biological Entity Extraction using the HUNER Dataset

Scope of the seminar

The purpose of this seminar is to help you to broaden your expertise in Machine Learning (ML) and Artificial Intelligence (AI). Therefore, well will introduce to you selected ML&AI technologies and tools relevant for your chosen seminar projects. You will acquire hands-on experience with these tools and apply them to real-world scenarios. We will equip you with the required ML&AI expertise and provide you access to materials for your chosen projects. We expect from you to deep dive in the required ML/AI technology, to learn about related work, to design and apply your own ML/AI approach, and to evaluate your approach and compare it to results from related work.   

You will select your preferred project topic from a list of topics presented in the kick-off lecture. We will coach you throughout the whole semester with regards to the chosen project. Furthermore, we will support you to improve your research and presentation skills. You will share your results in intermediate and final presentations together with all participants. You will document your final results in a scientific way.


The final grading will be determined by the following individual parts, where each of them must be passed individually: 

  • Intermediate presentation and final presentation (40%)
  • Research article (40%)
  • Individual commitment (20%)