How Neural Networks Learn

Intermediate · 5 concepts · 5 clips · 6 source videos. Watch the clips in order, then take the quick check to see what did not land.

What a network is

Layers of weighted sums with a squashing function. The structure is simple; what it can represent is not.

3Blue1Brown builds up neurons, layers and why a layered structure might learn anything at all (2:42-11:34)

Did this clip teach it?

Source videos · 6

3Blue1Brown
Grant Sanderson. The definitive visual explanation of transformers and attention. Mathematical without requiring the maths up front.
But What Is a Neural Network? | Deep Learning Chapter 1
Watch full video
3Blue1Brown
Grant Sanderson. The definitive visual explanation of transformers and attention. Mathematical without requiring the maths up front.
Gradient Descent, How Neural Networks Learn | Deep Learning Chapter 2
Watch full video
3Blue1Brown
Grant Sanderson. The definitive visual explanation of transformers and attention. Mathematical without requiring the maths up front.
Backpropagation, Intuitively | Deep Learning Chapter 3
Watch full video
StatQuest (Josh Starmer)
The standard reference for statistics and machine learning fundamentals. Works every idea through a small numerical example rather than a formula.
Neural Networks Pt. 2: Backpropagation Main Ideas
Watch full video
deeplizard
Deep learning mechanics in short segments. Useful for the training-failure nodes that intros skip.
Vanishing & Exploding Gradient Explained
Watch full video
Andrej Karpathy
Founding member of OpenAI, former director of AI at Tesla. Explains the systems he helped build, from first principles.
The Spelled-Out Intro to Neural Networks and Backpropagation: Building Micrograd
Watch full video

Ask the sources

Answers are drawn only from the clips on this path. Click a citation to jump the player to that concept.