📚 Syllabus & Course Curriculum
AI & Machine Learning in Healthcare
Module-by-module breakdown of Advanced Machine Learning, from foundations to a certified capstone project.
Theory
• Bias-variance decomposition and its limits as an explanation
• Regularisation viewed as constraint and as prior
• Why over-parameterised models generalise better than classical theory predicts
Ensembles
• Bagging, boosting and stacking, and the errors each reduces
• Gradient boosting internals and hyperparameter interaction
• Ensemble diversity and when combination stops helping
Probabilistic
• Bayesian inference, priors and posterior predictive checks
• Gaussian processes and their scaling constraints
• Calibration, conformal prediction and reliable uncertainty intervals
Causal
• Potential outcomes, confounding and identification assumptions
• Uplift modelling and heterogeneous treatment effects
• Why a predictive model cannot answer an interventional question
Robustness
• Distribution shift: covariate, label and concept
• Adversarial examples and robustness-accuracy trade-offs
• Monitoring, retraining triggers and safe degradation
Earn government-registered certification in Advanced Machine Learning
e-Certificate and e-Marksheet issued on successful completion.
