Backpropagation calculus | Deep Learning Chapter 4
What it is
3Blue1Brown's chapter 4 on deep learning gives a more formal, symbol-based account of backpropagation calculus, connecting the intuition from the previous chapter to the math found in textbooks and code.
Why Hacker News recommends it
Recommended as an accessible, visual way to understand backpropagation and neural networks.
- 3 people recommended it
- 2 different months
- 0 strong recommendations
- first 2017, last 2024
What HN commenters said
“here are the first few videos of the series”
Visual series on neural networks and backpropagation
nouveaux, 2017-11 · Recommendation · in “What is backpropagation and what is it doing? [video]”
“3Blue1Brown which explains math in very accessible way”
Accessible explanation of deep neural networks that removed fear of ML
hal9000xp, 2017-11 · Recommendation · in “Ask HN: Best way to get started with AI?”
“I find these 2 sources amazing”
Intuitive explanation of backpropagation akin to autodiff
melvinroest, 2020-06 · Recommendation · in “From scratch: reverse-mode automatic differentiation (in Python)”
Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.
Topics: backpropagation, neural networks, calculus, gradient descent, 3blue1brown
Also recommended by the same people
explainerBut what is a neural network? | Deep learning chapter 13Blue1Brown · 16 HN recommenders · 2017–2025
explainerBackpropagation, intuitively | Deep Learning Chapter 33Blue1Brown · 4 HN recommenders · 2017–2024
explainerGradient descent, how neural networks learn | Deep Learning Chapter 23Blue1Brown · 4 HN recommenders · 2017–2024
lectureThe spelled-out intro to neural networks and backpropagation: building microgradAndrej Karpathy · 17 HN recommenders · 2022–2025
documentaryAlphaGo - The Movie | Full award-winning documentaryGoogle DeepMind · 10 HN recommenders · 2020–2025
explainerTransformers, the tech behind LLMs | Deep Learning Chapter 53Blue1Brown · 13 HN recommenders · 2024–2026
talkUSENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible?USENIX · 10 HN recommenders · 2018–2026
courseLecture 1 | Machine Learning (Stanford)Stanford · 11 HN recommenders · 2008–2020