Phase 0: Neural Network Foundations · ~90 minutes · Python

Multi-Layer Networks and Forward Pass

One neuron draws a line. Stack them, and you can draw anything.

Hiring signal: Understanding of multi-layer networks and forward pass internals

What you will learn

Build a multi-layer network from scratch with Layer and Network classes that perform a complete forward pass
Trace matrix dimensions through each layer of a network and identify shape mismatches
Explain how stacking nonlinear activations enables a network to learn curved decision boundaries
Solve the XOR problem using a 2-2-1 architecture with hand-tuned sigmoid weights

Introduction

Type: Build Languages: Python Prerequisites: Phase 01 (Math Foundations), Lesson 03.01 (The Perceptron) Time: ~90 minutes

Learning Objectives

Build a multi-layer network from scratch with Layer and Network classes that perform a complete forward pass
Trace matrix dimensions through each layer of a network and identify shape mismatches
Explain how stacking nonlinear activations enables a network to learn curved decision boundaries
Solve the XOR problem using a 2-2-1 architecture with hand-tuned sigmoid weights

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build It, Use It, Ship It, Exercises, Key Terms, Further Reading — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.