neural_network_basics.md

Neural Network Basics

Make sure you understand linear algebra and derivatives (see prerequisites.md).

---

Start with this excellent animated walkthrough of neural networks and backpropagation:

• Neural Networks (chapter 1 - chapter 4) by 3Blue1Brown

---

Structured Learning with Dive into Deep Learning (D2L)

We recommend following these chapters in order:

• Chapter 1. Introduction: https://d2l.ai/chapter_introduction/index.html
• Chapter 2. Preliminaries: https://d2l.ai/chapter_preliminaries/index.html
• Chapter 3. Linear Neural Networks for Regression: https://d2l.ai/chapter_linear-regression/index.html
• Chapter 4. Linear Neural Networks for Classification: https://d2l.ai/chapter_linear-classification/index.html
• Chapter 5. Multilayer Perceptrons: https://d2l.ai/chapter_multilayer-perceptrons/index.html

The remaining chapters go deeper into advanced architectures and training techniques. Return to them once you've built a solid foundation.

Alternatively, you may use https://course.fast.ai/.

---

Understanding Backpropagation

• Michael Nielsen, Neural Networks and Deep Learning, chapter 2 - Helps build a conceptual understanding.
• Stanford CS231, Backpropagation, Intuitions - Precise and rigorous. Useful for understanding how gradients are computed.