Gradient descent, how neural networks learn | Deep Learning Chapter 2
Why Hacker News recommends it
HN recommends the series as a very accessible way to understand the math behind machine learning and LLMs.
What it is
3Blue1Brown's second neural network chapter explains cost functions and gradient descent, showing how a network learns by minimizing error during training.
Recommended by 4 HN commenters across 3 different months, 2017 to 2024.
What Hacker News said
Strong rec hal9000xp · 2017-11 · on “Ask HN: Best way to get started with AI?”
I'm in the same boat. For long time, I was interested in AI but at the same time intimidated by math. I'm relatively comfortable with discrete mathematics and classical algorithms and at the same time calculus and linear algebra is completely foreign to me. Also, I do not accept way to learn ML without good understanding of core principles behind it. So math is a must. A few months ago, I stumbled upon very amazing YouTube Channel 3Blue1Brown which explains math in very accessible way and at the same time I got feeling that I finally started understanding core ideas behind linear algebra and calculus. Just recently he published 4 videos about deep neural networks: [LINK] [this video] [LINK] [LINK
Recommends nouveaux · 2017-11 · on “What is backpropagation and what is it doing? [video]”
This was very timely for me and for anyone else learning, here are the first few videos of the series: [LINK] [this video] [LINK] (Original video) [LINK]
Recommends miklosme · 2020-05 · on “Humans Not Invited”
If you want an extensive answer, I recommend the neural network playlist on 3Blue1Brown: [LINK] For a quick answer, watch this segment: [this video]
Recommends superkuh · 2024-10 · on “LLMs Aren't Thinking, They're Just Counting Votes”
> when an LLM tells us that the sun rises in the east, it's not because it truly understands astronomy or the solar system. Rather, it has seen the phrase "sun rises in the east" repeated so many times in its training data that this becomes the highest probability answer. It's less about understanding and more about pattern recognition. This is not too different from most human person's experience with basic education ( [LINK] ). Though it is obvious that humans can do more than that too. And while "voting" that may be a close-enough metaphor for the multi-layer perceptron layers, it is not what is happening in the attention layers. I suggest checking out 3blue1brown's videos on gradient des
Cites afarrell · 2017-11 · on “What is backpropagation and what is it doing? [video]”
A bit of a side-note, but I think it is an interesting piece of marketing that Amplify Partners decided to sponsor[1] the previous video in this series. I wonder (and hope) we'll see more VCs sponsoring open educational content relevant to their focus. [1] [this video]