References: Neurons as numbers, layers as structure

Source material

Source curriculum (structural mirror, cited as further study):
• 3Blue1Brown, Neural Networks, Chapter 1: "But what is a Neural Network?"
  Creator: Grant Sanderson (text adaptation by Josh Pullen)
  Lesson page: https://www.3blue1brown.com/lessons/neural-networks
  Series index: https://www.3blue1brown.com/?topic=neural-networks
  License: copyright Grant Sanderson; videos published on his site and YouTube
This lesson mirrors the post-opener portion of Chapter 1, where the network's
layered structure is introduced. Clawdemy's lessons are original prose that
follows the pedagogical arc of this series. We do not reproduce or transcribe
the videos; we cite them as the recommended companion. All rights to the
original videos remain with the creator.

Watch this next

• But what is a Neural Network? (3Blue1Brown) by Grant Sanderson. The chapter this lesson mirrors. The section after the opening problem walks through exactly this structure, with the input layer, the two hidden layers, and the output layer animated so you can watch activations light up. If the layered picture felt abstract in text, the animation is the fastest way to make it move. About twenty minutes.

Going deeper

A short, durable list. Each link is a specific next step, not a generic pile.

• TensorFlow Playground. A neural network you can run in your browser with no setup. You can add and remove layers and neurons and watch the network’s behavior change in real time. The best way to turn “layers of neurons” from words into something you have actually touched. Do not worry about the training controls yet; just add a hidden layer, change the neuron count, and watch.

• Neural Networks and Deep Learning, Chapter 1 by Michael Nielsen. A free online book that introduces the same layered architecture for digit recognition and then carefully builds up how the numbers are computed. The natural deeper companion as you move into weights and biases in the next lesson.

Adjacent topics

Where this leads inside this track.

• Weights, biases, and the squish (lesson 3). This lesson said the hidden layers “do the work” of turning pixels into a guess, but not how. Lesson 3 answers it: what makes one neuron’s activation high or low is a weighted sum of the previous layer’s activations, plus a bias, squished into the 0-to-1 range.

• What “learning” really means (lesson 5). We described the structure as fixed, but the numbers that drive it are not handed down; they are learned from examples. Lesson 5 makes that precise.