hackertube.io

Gradient descent, how neural networks learn | Deep Learning Chapter 2

3Blue1Brown · explainer · Watch on YouTube

Machine learning & deep learning

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.

Why Hacker News recommends it

HN recommends the series as a very accessible way to understand the math behind machine learning and LLMs.

  • 4 people recommended it
  • 3 different months
  • 1 strong recommendations
  • first 2017, last 2024

What HN commenters said

  1. “3Blue1Brown which explains math in very accessible way”

    Accessible math explanation that removed fear of ML.

    hal9000xp, 2017-11 · Strong recommendation · in “Ask HN: Best way to get started with AI?”

  2. “here are the first few videos of the series”

    Part of a video series for learning neural networks.

    nouveaux, 2017-11 · Recommendation · in “What is backpropagation and what is it doing? [video]”

  3. “For a quick answer, watch this segment”

    Quick answer on how neural networks learn.

    miklosme, 2020-05 · Recommendation · in “Humans Not Invited”

  4. “I suggest checking out 3blue1brown's videos on gradient descent”

    Explains gradient descent, helpful for understanding LLMs.

    superkuh, 2024-10 · Recommendation · in “LLMs Aren't Thinking, They're Just Counting Votes”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: neural networks, cost function, machine learning, 3blue1brown, deep learning

Also recommended by the same people