The module provides an introduction into the principles of machine learning in healthcare and biomedicine, covering the key concepts involved in designing and evaluating approaches to machine learning. It will provide a practical introduction to common approaches to machine learning, so that students acquire experience in using different machine learning algorithms and concepts (i.e. decision trees, probabilistic classifiers, support vector machines, artificial neural nets, and ensembles) in the context of healthcare. As a pre-condition for this module you must have accomplished the two modules: (1) Scientific Software Development with Python in Health Research (SSDPHR) and (2) Principles of Health Data Science (PHDS).
Module code
CHME0016
UCL credits
15
Course Length
9 Weeks
Face to Face Dates
14:00 - 17:00
Jan: 12, 19, 26
Feb: 02, 09, 23
Mar: 02, 09, 16, 23
Assessment Dates
TBC
Module organiser
Dr Holger Kunz Please direct queries to courses-IHI@ucl.ac.uk
Content
- Machine learning
- Hyperparameter tuning and evaluation
- Probabilistic learning
- Decision tree learning
- Artificial neural netw
- Data pre-processing and dimensionality reduction
- Support vector machines
- Ensemble classifier
- Deep learning
Teaching and learning methods
This 15 credit module lasts for 10 weeks and should represent 150 learning hours. The module will use a mixture of lectures and computer-based practical using Python. There will be private reading and materials will be made available via Moodle, with some online activities.
Assessment
The final assessment will involve analysing an example data set and writing a report to answer the given research questions.