Course Roadmap

9 sections53 chapters

Access:

Difficulty:

#	Section / Chapter	Difficulty
1	Welcome
	Course Roadmap
	Join the Community
2	Introduction
	What is Machine Learning?
	What is ML System Design?
	ML vs Traditional System Design
3	ML Fundamentals
	Supervised vs Unsupervised Learning
	Classification vs Regression
	Common ML Algorithms
	Embeddings and Representation Learning
	Loss Functions and Optimization
	Bias-Variance Tradeoff
	Model Selection
	Framing ML Problems
4	Data Engineering for ML
	Data Collection Strategies
	Data Labeling at Scale
	Data Sampling and Augmentation
	Feature Engineering
	Feature Stores
	Data Pipelines
	Data Validation & Quality
	Handling Data Skew and Imbalance
5	Model Training
	Training Pipelines
	Distributed Training
	Transfer Learning and Fine-Tuning
	Hyperparameter Tuning
	Experiment Tracking
	Model Versioning
6	Model Evaluation
	Evaluation Metrics
	Offline Evaluation
	Online Evaluation
	A/B Testing for ML
	Model Fairness & Bias
7	Model Serving and Infrastructure
	Model Deployment Strategies
	Batch vs Real-time Inference
	Model Optimization
	Serving Infrastructure
	Model Caching
	Feature Serving
	Scaling ML Systems
	Cost Optimization for ML
8	MLOps
	ML Pipelines
	Model Monitoring
	Data & Model Drift Detection
	Model Retraining Strategies
	CI/CD for ML
9	ML Design Patterns
	Embedding-Based Retrieval
	Two-Tower Architecture
	Multi-Stage Ranking
	Cascade Models
	Ensemble Methods
	Knowledge Distillation
	Online Learning and Continual Training
	Active Learning