Chapter 3: Linear Algebra & Calculus¶
Understand the mathematics behind machine learning and neural networks.
Metadata¶
| Field | Value |
|---|---|
| Track | Foundation |
| Time | 10 hours |
| Prerequisites | Chapter 1 (Python Fundamentals) |
Learning Objectives¶
- Understand vectors, matrices, and tensor operations
- Apply linear algebra to ML problems with NumPy
- Grasp derivatives, partial derivatives, and gradients
- Understand the chain rule and backpropagation intuition
- Use numerical optimization basics
What's Included¶
Notebooks¶
| Notebook | Description |
|---|---|
01_introduction.ipynb | Vectors, norms, vector operations |
02_intermediate.ipynb | Matrices, matrix operations, NumPy |
03_advanced.ipynb | Gradients, backpropagation, optimization |
Scripts¶
linear_algebra_toolkit.py— Core linear algebra functionsutilities.py— Helper functions for the curriculum
Exercises¶
- 5 exercises with solutions (in
solutions/branch)
SVG Diagrams¶
- 3 visual diagrams for vector/matrix concepts
Read Online¶
You can read the full chapter content right here on the website:
- 03.1 Introduction -- Vectors, dot product, norms, cosine similarity
- 03.2 Intermediate -- Matrices, linear transformations, NumPy
- 03.3 Advanced -- Derivatives, gradients, chain rule, gradient descent capstone
Or try the code in the Playground.
How to Use This Chapter¶
Quick Start
Follow these steps to get coding in minutes.
1. Clone and install dependencies
git clone https://github.com/luigipascal/berta-chapters.git
cd berta-chapters
pip install -r requirements.txt
2. Navigate to the chapter
3. Launch Jupyter
GitHub Folder
All chapter materials live in: chapters/chapter-03-linear-algebra/
NumPy Required
This chapter relies heavily on NumPy. Ensure it's installed: pip install numpy
Created by Luigi Pascal Rondanini | Generated by Berta AI