Course notes
Teaching
Three self-contained learning paths move from core machine learning methods to deep architectures and explainable AI. Each module combines mathematical foundations with the practical judgment needed to use the methods well.
Machine Learning
Supervised and unsupervised learning, from linear models and trees to evaluation, tuning, and clustering.
Deep Learning
Neural-network foundations, optimization, regularization, and the convolutional architectures behind computer vision.
Explainability in AI
Methods for interpreting models, diagnosing behavior, and strengthening trust, fairness, and accountability.