AIAI Club
← All lessons
Meeting 1Forward propagation

How a neural network moves information

Goal: understand what a neuron receives, what a connection changes, and how values move forward through layers. This lesson stops at forward propagation; training and backpropagation come later.

Start the guided tutorialFive editable steps · no calculus needed
01

Watch the visual introduction

Use 3Blue1Brown's handwritten-digit example through 13:32. Stop before the compact vector and matrix notation begins.

Open “But what is a neural network?” ↗
02

Walk through five networks

Open the playground and change presets in this order:

  1. 1 → 1Follow one input across one weighted connection.
  2. 2 → 1See how a neuron combines more than one input.
  3. 1 → 2 → 1Introduce a hidden layer and two intermediate values.
  4. 2 → 2 → 1Compare several weighted paths through the same layer.
  5. 3 → 3 → 2Finish with multiple inputs, hidden neurons, and outputs.
Open Neural Network Playground →
03

Let members change one thing

Select an input, connection, or node. Change its value, weight, or bias and observe which later values move. Keep the activation on ReLU: negative becomes 0, while a positive value stays unchanged.

Resources inside this lesson

Related references