Library/microgradForked

karpathy/micrograd

micrograd

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

View on GitHub↗Upstream karpathy/micrograd↗

Builder

karpathy

karpathy • individual

Stars

15,309

Using upstream star count

Forks

2,322

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Apr 13, 2020

Project creation date

README Summary

Micrograd is a tiny scalar-valued automatic differentiation engine implemented in about 50 lines of Python code. It provides a PyTorch-like API for building and training neural networks, serving as an educational tool to understand how autograd engines work under the hood. The library demonstrates backpropagation and gradient computation through a simple but complete implementation.

AI Dev Skills

Unmapped

Automatic DifferentiationBackpropagation ImplementationNeural Network FundamentalsComputational Graph ConstructionGradient-based OptimizationEducational Deep Learning

Taxonomy

AI Trends

Educational AI Interpretable AI

Deployment Context

Self-hosted Browser/WASM

Industries

Education

Modalities

Tabular

Skill Areas

Automatic Differentiation Backpropagation Implementation Neural Network Fundamentals Computational Graph Construction Gradient-based Optimization Educational Deep Learning

Use Cases

Deep Learning Education Understanding Autograd Mechanics Learning Neural Network Fundamentals Prototyping Simple Neural Networks

Recent Activity

Updated 1 years ago

7 Days

30 Days

90 Days

Quality

research

Quality: medium
Maturity: research

PM Skills

Developer Platform

Languages

Jupyter Notebook100.0%

Timeline

Project created: Apr 13, 2020
Forked: Mar 16, 2026
Your last push: 1 years ago
Upstream last push: 1 years ago
Tracked since: Aug 8, 2024

Similar Repos

pgvector cosine similarity · $0

Loading…