karpathy/micrograd
micrograd
A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API
Builder
karpathy
karpathy • individual
Stars
16,082
Using upstream star count
Forks
2,505
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Apr 13, 2020
Project creation date
README Summary
A tiny Autograd engine (with a bite! :)). Implements backpropagation (reverse-mode autodiff) over a dynamically built DAG and a small neural networks library on top of it with a PyTorch-like API. Both are tiny, with about 100 and 50 lines of code respectively. The DAG only operates over scalar values, so e.g. we chop up each neuron into all of its individual tiny adds and multiplies. However, this is enough to build up entire deep neural nets doing binary classification, as the demo notebook sho
Community Evaluation
Loading…AI Dev Skills
Unmapped
Automatic DifferentiationBackpropagation ImplementationComputational Graph ConstructionEducational Deep LearningGradient-based OptimizationNeural Network Fundamentals
Tags
Automatic DifferentiationBackpropagation ImplementationComputational Graph ConstructionEducational Deep LearningGradient-based OptimizationNeural Network FundamentalsDeep LearningForkedJupyterPyTorchPython
Taxonomy
AI Trends
Deployment Context
Industries
Modalities
Skill Areas
Recent Activity
Updated 1 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- medium
- Maturity
- research
Categories
Data Science & AnalyticsPrimaryModel TrainingOther AI / ML
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…