References: The whole network as one function

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 closing portion of Chapter 1, where the structure and
the per-neuron computation come together as one function. 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 four-lesson arc has mirrored end to end. Watching the full network light up layer by layer, with the forward pass animated from input to output, is the payoff that ties the structure and the per-neuron formula together. If you watch one thing after this lesson, watch the closing minutes where the whole network runs.

Going deeper

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

• TensorFlow Playground. The browser network from the last two lessons. Now that you understand the forward pass, hit the play button and watch outputs change as data flows through; you are watching f(x; w, b) evaluated live. Still hold off on reading deeply into the training controls; lesson 5 is where those start to make sense.

• Neural Networks and Deep Learning, Chapter 1 by Michael Nielsen. Presents the network as a function of its weights and biases and works a full forward pass in matrix form. The natural deeper read if you want to see the same assembly written more formally.

Adjacent topics

Where this leads inside this track.

• What “learning” really means (lesson 5). This lesson reframed building a network as a search: out of a vast space of possible weight-and-bias settings, find one that makes the function behave. Lesson 5 starts on how that search actually works, beginning with how we measure “how wrong” the network currently is.

• The cost function and gradient descent (lessons 5 to 7). The search needs a compass. Those lessons introduce a way to score the network’s wrongness and a method for stepping the parameters in the direction that reduces it.