Understanding Automatic Differentiation in 30 lines of Python

• micrograd

  22 8,273 0.0 Jupyter Notebook

  A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

• GPU-Puzzles

  12 5,022 3.4 Jupyter Notebook

  Solve puzzles. Learn CUDA.

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• Tensor-Puzzles

  9 2,450 4.3 Jupyter Notebook

  Solve puzzles. Improve your pytorch.

• picoGPT

  7 3,081 1.9 Python

  An unnecessarily tiny implementation of GPT-2 in NumPy.

In that case, you might also enjoy https://jaykmody.com/blog/gpt-from-scratch/

(here's the raw code: https://github.com/jaymody/picoGPT/blob/main/gpt2.py)

• mercury-ad

  2 6 10.0 Mercury

  Mercury library for automatic differentiation

I wrote a purely functional AD library in Mercury [0], which adapts a general approach from [1]. I believe that Owl provides a similar approach [2].

[0] https://github.com/mclements/mercury-ad

• AD-Rosetta-Stone

  2 26 10.0 Scala

  Examples of Automatic Differentiation (AD) in many different languages and systems

[1] https://github.com/qobi/AD-Rosetta-Stone/

• owl

  5 1,178 8.2 OCaml

  Owl - OCaml Scientific Computing @ https://ocaml.xyz

  

• WorkOS

  workos.com sponsored

  The modern identity platform for B2B SaaS. The APIs are flexible and easy-to-use, supporting authentication, user identity, and complex enterprise features like SSO and SCIM provisioning.

  

• SmallPebble

  6 112 0.0 Python

  Minimal deep learning library written from scratch in Python, using NumPy/CuPy.

Suggest a related project