Gradient descent, how neural networks learn | Deep Learning Chapter 2
Gradient descent, how neural networks learn | Deep Learning Chapter 2 on HackerTube: recommended by 4 Hacker News commenters across 3 separate months, 2017–2024.
3Blue1Brown's second neural network chapter explains cost functions and gradient descent, showing how a network learns by minimizing error during training.
What HN commenters said
5 Hacker News comments link this video. Each one links back to its thread.
hal9000xpNov 2017Strongly recommends
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] So my fear of ML was gone away and I'm very excited to explore whole new world for neural networks and other things like support vector machines etc
in “Ask HN: Best way to get started with AI?” · View on HN
superkuhOct 2024Recommends
> 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 descent ▶ this video and "How might LLMs store facts" [link] versus how attention works [link]
in “LLMs Aren't Thinking, They're Just Counting Votes” · View on HN
miklosmeMay 2020Recommends
If you want an extensive answer, I recommend the neural network playlist on 3Blue1Brown: [link] For a quick answer, watch this segment: ▶ this video
in “Humans Not Invited” · View on HN
nouveauxNov 2017Recommends
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]
in “What is backpropagation and what is it doing? [video]” · View on HN
afarrellNov 2017Cites it
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
in “What is backpropagation and what is it doing? [video]” · View on HN