📘 Picking Up Machine Learning (Systematically)

If you're interested in learning ML in a structured way, here’s a curated set of textbooks, lectures, and online resources.

---

📚 Core Textbooks

Machine Learning

1. Pattern Recognition and Machine Learning – Christopher Bishop
   A foundational ML book that covers theory and methods.

2. Hands-On Machine Learning with Scikit-Learn and TensorFlow – Aurélien Géron
   Practical and surprisingly thorough; excellent explanations of neural networks.

3. Learning from Data – Yaser Abu-Mostafa
   Concise and accessible, with some deep insights.

4. Elements of Statistical Learning – Hastie, Tibshirani, Friedman (Free online)
   A classic, mathematically rigorous book for statistical ML.

5. Machine Learning: A Probabilistic Perspective – Kevin Murphy
   Advanced ML reference; best after mastering the basics.

---

Probability & Statistics

1. Introduction to Probability – Bertsekas & Tsitsiklis
   Start here if you’re new to probability and statistics.

2. Probability Theory: The Logic of Science – E.T. Jaynes
   Philosophically rich and very well-written.

3. Statistical Inference – Casella & Berger
   More advanced treatment of inference.

---

🎥 Video Lectures

• Mathematical Monk YouTube Series
• Learning from Data – Caltech

---

🧠 Neural Networks & Deep Learning

General

• Applied Deep Learning Series – Towards Data Science

CNNs

• CS231n – Stanford CNN Course

RNNs

• WildML – RNN Introduction
• Distill – Augmented RNNs

Attention & Transformers

• Transformers Overview – Towards Data Science
• Illustrated Transformer – Jay Alammar

---

📄 Blogs & Articles

• Colah's Blog

Selected Blog Posts

• Bias in Time Series Regressions – Alex Chinco
• How to Interpret P-Value Histograms – Variance Explained ⭐
• K-Means & Free Lunch – Variance Explained