sutskever-30-implementations

Small educational NumPy implementations, as Jupyter notebooks, of the 30 papers on Ilya Sutskever's reading list. Useful for learning core deep learning ideas by running simple code.

Browse open issues

Pick a small issue you can reproduce, then fix it with your AI coding agent.

Share on XNo license declared

Overview

This repository contains small educational implementations of the 30 papers on Ilya Sutskever's reading list, written as Jupyter notebooks. Each notebook uses only NumPy, with no deep learning framework, and generates its own synthetic data so it runs straight away. Visualizations and explanations accompany the code. The README reports all 30 papers as complete.

Key features

  • One notebook per paper, covering all 30 papers
  • Uses only NumPy, with no deep learning framework
  • Synthetic data included, so notebooks run immediately
  • Visualizations and explanations of each core idea
  • Topics include RNNs, LSTMs, pruning and more

Best for

Learners who want to understand core deep learning ideas by running simple code instead of large frameworks. These are toy versions meant for teaching, not for production use.

Upstream
pageman/sutskever-30-implementations
Fork on GitHub
Guo-astro/sutskever-30-implementations
Upstream stars
5.2k
Category
Learning, interviews and curated lists
License
No license declaredWithout a license, the author keeps all rights. Ask the upstream owner before reusing the code.
Forked
2026-08-17
Sync status
In syncLast synced 2026-10-20

More in Learning, interviews and curated lists