This advanced course builds on the introductory machine learning course and focuses on modern deep learning methods for health research. Participants will gain hands-on experience with key model architectures, including convolutional neural networks, autoencoders, diffusion models, and transformers. 

The course combines lectures with practical coding sessions, where participants train models on real or realistic health-related datasets using GPU-based computing. Emphasis is placed on understanding when and how to apply these methods in epidemiological and clinical research, as well as recognizing their limitations in real-world settings. 

Objectives

• Understand advanced deep learning architectures used in health research  

• Train and evaluate models using real-world health data  

• Recognize challenges such as bias, overfitting, and generalizability  

• Translate advanced methods into meaningful clinical or epidemiological applications 

Participant profile

Clinical researchers, epidemiologists, data scientists, biostatisticians and engineers in healthcare as well as PhD Students.

Assessment