Contains notes from COMP9417 (Machine Learning and Data Mining). Received HD in the subject. TOPICS For Supervised learning: - Regression (linear vs non-linear, parameter estimation, train, validation and test data, bias-variance tradeoff, etc.) - Classification I & II (binomial classification, normalisation, nearest neighbour, KNN, Naive Bayes, etc.) - Tree learning (decision trees, entropy, pruning, splitting, etc.) - Kernel methods (perception algorithm, non-linear and soft margin SVMs, etc.) - Ensemble learning (bias-variance decomposition, bagging, randomisation, AdaBoost, etc.) - Neural learning (multilayer perceptions, gradient descent, back-propagation, CNN, etc.) and Unsupervised learning (K-means clustering, EM, hierarchical clustering, PCA, etc.).