Durable AI/ML fundamentals organized the way a researcher keeps notes: definitions, assumptions, failure modes, experiments, and implementation consequences.
Core language, NumPy, Pandas, async patterns, and performance optimization for production AI systems.
Learning theory, model families, evaluation methodology, and workflow patterns with production context.
Probability, inference, uncertainty quantification, and A/B experimentation frameworks.
Representation learning, optimization, modern architectures, and systems-level thinking for production DL.