Phase 0: Neural Network Foundations · ~120 minutes · Python

Backpropagation from Scratch

Backpropagation is the algorithm that makes learning possible. Without it, neural networks are just expensive random number generators.

What you will learn

Implement a Value-based autograd engine that builds a computational graph and computes gradients via topological sort
Derive the backward pass for addition, multiplication, and sigmoid using the chain rule
Train a multi-layer network on XOR and circle classification using only your from-scratch backpropagation engine
Identify the vanishing gradient problem in deep sigmoid networks and explain why gradients shrink exponentially

Introduction

Type: Build
Languages: Python
Prerequisites: Multi-Layer Networks and Forward Pass
Time: ~120 minutes

Objective

Learning objectives

Implement a Value-based autograd engine that builds a computational graph and computes gradients via topological sort
Derive the backward pass for addition, multiplication, and sigmoid using the chain rule
Train a multi-layer network on XOR and circle classification using only your from-scratch backpropagation engine
Identify the vanishing gradient problem in deep sigmoid networks and explain why gradients shrink exponentially

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account — the opening phases of 29 of 35 courses are free, no credit card.

Key terms in this lesson

Backpropagation