📚 Syllabus & Course Curriculum
AI & Machine Learning in Healthcare
Module-by-module breakdown of Machine Learning in Research: From Fundamentals to Advanced Applications, from foundations to a certified capstone project.
Method
• Prediction versus explanation as distinct research goals
• When a simpler statistical model answers the question better
• Framing a research question that machine learning can genuinely address
Rigour
• Nested cross-validation and honest performance estimation
• Data leakage in research datasets and how reviewers detect it
• Baselines and ablations that make a claim credible
Small Data
• Regularisation, transfer learning and data augmentation for small cohorts
• Uncertainty quantification when sample size is the binding constraint
• Recognising when the dataset cannot support the intended conclusion
Interpretation
• Feature attribution and its correct interpretation in a research claim
• Generating hypotheses for experimental follow-up
• Avoiding narrative overfitting to model output
Reporting
• Reporting checklists for machine learning in scientific journals
• Releasing code, data and environment for replication
• Responding to methodological review comments
Earn government-registered certification in Machine Learning in Research: From Fundamentals to Advanced Applications
e-Certificate and e-Marksheet issued on successful completion.
