Machine Learning — resources
roadmap.sh: https://roadmap.sh/machine-learning
Books
- Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow (Aurélien Géron) — the most practical end-to-end intro; code-first, covers classic ML through deep learning with real projects.
- An Introduction to Statistical Learning (James, Witten, Hastie, Tibshirani) — gentle but rigorous grounding in the statistics behind ML; free PDF and approachable R/Python labs.
- Pattern Recognition and Machine Learning (Christopher Bishop) — the deep theoretical reference for probabilistic ML; reach for it when you want the math behind the methods.
- Deep Learning (Goodfellow, Bengio, Courville) — canonical free textbook for neural networks, optimization, and modern architectures.
Courses / practice
- Andrew Ng — Machine Learning Specialization (Coursera/DeepLearning.AI) — the classic foundations course, now in Python; best starting point for intuition.
- fast.ai — Practical Deep Learning for Coders — top-down, build-models-first approach to deep learning; great once you know basic Python.
- Kaggle Learn + Competitions — short hands-on micro-courses plus real datasets and competitions to practice the full pipeline.