ML Core (Overview)

Goal: keep your ML fundamentals sharp enough to explain tradeoffs clearly under interview pressure.

Navigation

• Use 20-ML-Core/Module Map to jump by module or guide section.

Core modules (in order)

1. 20-ML-Core/Module 01 - Math Foundations + Classical ML
2. 20-ML-Core/Module 02 - Deep Learning Foundations
3. 20-ML-Core/Module 03 - CNNs, RNNs, Transformers
4. 20-ML-Core/Module 04 - PyTorch Practice

Deep-dive guide

• 20-ML-Core/Guide/Overview
• 20-ML-Core/Guide/Math Foundations (Guide)
• 20-ML-Core/Guide/Classical Machine Learning (Guide)
• 20-ML-Core/Guide/Deep Learning (Guide)
• 20-ML-Core/Guide/Specialized Topics (Guide)
• 20-ML-Core/Guide/Interview Question Bank (Guide)

Companion references

• 20-ML-Core/ML Cheat Sheet
• 20-ML-Core/Concepts Tracker

What to aim for in interviews

• Explain bias/variance, regularization, and evaluation metrics
• Derive backprop at a high level (chain rule intuition)
• Compare architectures (CNN vs RNN vs Transformer) and training tradeoffs