1. Math & Statistics for ML
2. Programming & Engineering
3. AI Systems
4. Data Science & Analytics
5. Machine Learning
5.1. Learning Paradigms
5.1.1. Supervised Learning
5.1.2. Unsupervised Learning
5.1.3. Semi-supervised Learning
5.1.4. Self-supervised Learning
5.1.5. Reinforcement Learning
5.1.6. Online & Active Learning
5.1.7. Transfer & Multi-task Learning
5.2. Algorithms & Model Families
5.2.1. Linear Models
5.2.2. Tree-based Models
5.2.3. Enseble Models
5.2.4. Distance-/Similarity-Based Models
5.2.5. Probabilistic Models
5.2.6. Neural Networks & Deep Learning
5.3. Core Modeling Concepts
5.3.1. Feature Engineering & Selection
5.3.2. Model Evaluation & Selection
5.3.3. Overfitting, Regularization & Generalization
5.3.4. Bias-Variance Trade-Off
5.3.5. Interpretability & Explainability
5.4. Lifecycle & MLOps
5.4.1. Problem Scoping & Business Alignment
5.4.2. Data Collection, Versioning & Feature Stores
5.4.3. Experiment Tracking & Hyperparameter Tuning
5.4.4. Deployment & CI/CD Pipelines
5.4.5. Monitoring, Drift & Retraining
5.4.6. Governance, Fairness, Privacy & Auditability
5.4.7. Reference Frameworks