Module 1 – Introduction to Deep Learning

What you'll learn

None — start here

≈6 h · 2 h video · 2 h reading · 2 h coding

Compute matrix–vector products and visualize linear transforms
Explain XOR nonlinearity and demonstrate failure → fix with ReLU
Implement a minimal MLP with PyTorch tensors/modules and describe SGD updates

Lecture 1 – From Linear Regression to Neural Networks

Lecture 1.2 – Linear Regression via Neural Networks in Python

📚 Resources & Lecture Code

Required reading · course book

Ch. 1 · Linear Regression, the Mother Model
Ch. 2 · Linear Models that Classify
Ch. 3 · Nonlinearity and the MLP
Ch. 4 · Training: Loss and SGD
Appendix A · Linear Algebra and the SVD
Appendix B · Tensors in Practice
Appendix D · Notation
Appendix E · Statistical Learning Contracts

These Colab notebooks contain the lecture codes demonstrated in class and help you with the homework 1. Read the instructions at the top and run the cells in order.

Open Colab Notebook 1

Open Colab Notebook 2

Start of course

Module 2