nn-zero-to-hero

Source

Classification

Summary

Neural Networks: Zero to Hero A course on neural networks that starts all the way at the basics. The course is a series of YouTube videos where we code and train neural networks together. The Jupyter notebooks we build in the videos are then captured here inside the $1 directory. Every lecture also has a set of exercises included in the video description. (This may grow into something more respectable). --- Lecture 1: The spelled-out intro to neural networks and backpropagation: building micrograd Backpropagation and training of neural networks. Assumes basic knowledge of Python and a vague recollection of calcul…

What This Teaches

  • How core neural network ideas can be rebuilt from first principles.
  • Useful for grounding later LLM work in gradients, activations, optimization, and model internals.

Why It Matters

This is high-priority for Vipin because it supports durable first-principles understanding instead of shallow API use.

Repository Snapshot

  • Full name: karpathy/nn-zero-to-hero
  • Default branch: master
  • HEAD: 73c3fcc741f0ec104ca850b1fb0df90e7e8d4cde
  • Stars at crawl: 21842
  • Forks at crawl: 3204
  • File count: 9
  • README path: README.md
  • License path: LICENSE
  • Created: 2022-09-08T21:23:25Z
  • Updated: 2026-05-15T20:59:39Z
  • Pushed: 2024-08-18T12:16:26Z

Top-Level Structure

  • lectures: 7
  • [root]: 2

File Extension Profile

  • .ipynb: 7
  • .md: 1
  • [none]: 1

Tags / Release-Like Markers

  • No git tags found in the shallow local clone.

Sample File Tree

  • lectures/makemore/makemore_part1_bigrams.ipynb
  • lectures/makemore/makemore_part2_mlp.ipynb
  • lectures/makemore/makemore_part3_bn.ipynb
  • lectures/makemore/makemore_part4_backprop.ipynb
  • lectures/makemore/makemore_part5_cnn1.ipynb
  • lectures/micrograd/micrograd_lecture_first_half_roughly.ipynb
  • lectures/micrograd/micrograd_lecture_second_half_roughly.ipynb
  • LICENSE
  • README.md

Public Handling Notes

  • EXTRACTED: This page records public metadata and a source-grounded summary.
  • INFERRED: Full local preservation, when available, is for private/local use unless a license or explicit source policy makes public redistribution safe.
  • Do not treat this page as permission to republish unlicensed source text or code wholesale.