References: The cost landscape

Source material

Source curriculum (structural mirror, cited as further study):
• 3Blue1Brown, Neural Networks, Chapter 2: "Gradient descent, how neural networks learn"
  Creator: Grant Sanderson (text adaptation by Josh Pullen)
  Lesson page: https://www.3blue1brown.com/lessons/gradient-descent
  Series index: https://www.3blue1brown.com/?topic=neural-networks
  License: copyright Grant Sanderson; videos published on his site and YouTube
This lesson mirrors the cost-landscape portion of Chapter 2, where cost is
pictured as a surface and the gradient 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

• Gradient descent, how neural networks learn (3Blue1Brown) by Grant Sanderson. The chapter this lesson mirrors. The middle section animates exactly the picture built here: a ball on a 2D cost surface, the slope at its feet, and the downhill direction. Seeing the surface tilt and the ball find a valley is the fastest way to lock in the landscape intuition.

Going deeper

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

• The Essence of Calculus (3Blue1Brown) by Grant Sanderson, and Clawdemy’s own Track 8 (Visual Math: Calculus). This lesson leaned on “the slope at a point” without defining it precisely. If that idea felt shaky, the derivative is exactly what makes it precise, and both of these build it from scratch.

• Neural Networks and Deep Learning, Chapter 1 (gradient descent section) by Michael Nielsen. Introduces the same valley-and-ball picture and then connects it to the formula for the gradient. The natural deeper read once you want the math under the metaphor.

• TensorFlow Playground. Press play and watch the loss fall step by step. You are watching a walk downhill across a cost landscape exactly like the one in this lesson, one small step at a time.

Adjacent topics

Where this leads inside this track.

• What “learning” really means (lesson 5). The previous lesson defined the cost we are picturing here. If the landscape feels untethered, lesson 5 is where the height at each point, the cost, comes from.

• Gradient descent (lesson 7). This lesson built the terrain and the compass. Lesson 7 takes the walk: start somewhere, read the negative gradient, step, and repeat. It is the algorithm this whole chapter is named for, and it handles the practical questions this lesson set aside, like how big a step to take and when to stop.