awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
karpathy avatar

karpathy/micrograd

0
View on GitHub↗

Micrograd

micrograd is a scalar autograd engine and minimal neural network library. It implements a system for reverse-mode automatic differentiation over a dynamic graph of scalar operations to calculate gradients.

The project includes a computation graph visualizer that generates representations of data flow and gradient propagation. It provides a set of tools for constructing and training multi-layer perceptrons using an API modeled after PyTorch.

The library covers the fundamentals of backpropagation and neural network construction, specifically for binary classification tasks. This includes the implementation of automatic gradient computation and layer-based model abstractions.

The project is provided as a Jupyter Notebook.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Features

  • Automatic Differentiation - Implements a reverse-mode automatic differentiation engine using the chain rule to compute gradients.
  • Automatic Differentiation Engines - Implements a custom engine that computes gradients of mathematical functions by traversing computational graphs.
  • Backpropagation - Implements the backpropagation algorithm to calculate gradients of loss functions for updating model parameters.
  • Neural Network Training Frameworks - Provides a minimal library for constructing and training multi-layer perceptrons using a PyTorch-like API.
  • Neural Network Module Abstractions - Provides high-level class abstractions to encapsulate neural network layers, weights, and biases.
  • Autograd Engines - Implements a small reverse-mode automatic differentiation engine over a dynamic graph of scalar operations.
  • Scalar Primitives - Uses scalar-based primitives that maintain gradient state and local derivative logic.
  • Directed Acyclic Graph Engines - Builds a dynamic directed acyclic graph to track scalar operations and their dependencies for gradient calculation.
  • Computational Graph Visualizations - Generates visual representations of the computational graph to show data flow and gradient propagation.
  • Neural Network Classification - Provides the ability to construct and train multi-layer perceptrons for binary classification tasks.
  • Neural Network Construction - Enables the design and building of deep learning architectures using layer-based model abstractions.
  • Deep Learning Education - Serves as an educational resource for learning neural network theory and backpropagation via a minimal implementation.
  • Model Training - Lightweight autograd engine for educational purposes.
  • Model Training Frameworks - Lightweight autograd engine for understanding neural network foundations.
16,455 stars·2,587 forks·Jupyter Notebook·MIT·39 views

Star history

Star history chart for karpathy/microgradStar history chart for karpathy/micrograd

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

Frequently asked questions

What does karpathy/micrograd do?

micrograd is a scalar autograd engine and minimal neural network library. It implements a system for reverse-mode automatic differentiation over a dynamic graph of scalar operations to calculate gradients.

What are the main features of karpathy/micrograd?

The main features of karpathy/micrograd are: Automatic Differentiation, Automatic Differentiation Engines, Backpropagation, Neural Network Training Frameworks, Neural Network Module Abstractions, Autograd Engines, Scalar Primitives, Directed Acyclic Graph Engines.

Which projects share features with karpathy/micrograd?

Projects with overlapping indexed features include: johnmyleswhite/ml_for_hackers — ML for Hackers is a machine learning educational resource and library designed for learning the fundamentals of… tingsongyu/pytorch-tutorial-2nd — This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It… facebookresearch/flashlight — Flashlight is a C++ machine learning library and deep learning framework designed for building and training neural… astorfi/tensorflow-world — TensorFlow-World is a collection of tutorials, implementation guides, and model templates for building and training… snowkylin/tensorflow-handbook — This project is a comprehensive educational resource and tutorial handbook for building, training, and deploying… ashishpatel26/andrew-ng-notes — This project is a collection of structured study notes and notebooks serving as an educational resource for deep…

Projects sharing features with Micrograd

These projects share indexed features with Micrograd. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • johnmyleswhite/ml_for_hackersjohnmyleswhite avatar

    johnmyleswhite/ML_for_Hackers

    3,737View on GitHub↗

    ML for Hackers is a machine learning educational resource and library designed for learning the fundamentals of algorithmic programming and data analysis. It provides a neural network framework and a collection of mathematical implementations for building and training predictive models. The project utilizes a modular architecture for stacking linear transformations and activation layers. It implements core deep learning components from scratch using multi-dimensional arrays for tensor algebra and operations. The framework covers a variety of algorithmic capabilities, including automatic diff

    R
    View on GitHub↗3,737
  • tingsongyu/pytorch-tutorial-2ndTingsongYu avatar

    TingsongYu/PyTorch-Tutorial-2nd

    4,555View on GitHub↗

    This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen

    Jupyter Notebookcomputer-visiondeepsortdiffusion-models
    View on GitHub↗4,555
  • facebookresearch/flashlightfacebookresearch avatar

    facebookresearch/flashlight

    5,443View on GitHub↗

    Flashlight is a C++ machine learning library and deep learning framework designed for building and training neural networks. It functions as a tensor manipulation library and an automatic differentiation engine that tracks operations to calculate gradients via backpropagation for model optimization. The project is distinguished by its role as a distributed training framework, utilizing all-reduce gradient synchronization and distributed environments to scale machine learning workloads across multiple nodes and devices. It features a backend-agnostic memory interface and RAII-based management

    C++
    View on GitHub↗5,443
  • astorfi/tensorflow-worldastorfi avatar

    astorfi/TensorFlow-World

    4,492View on GitHub↗

    TensorFlow-World is a collection of tutorials, implementation guides, and model templates for building and training machine learning models using the TensorFlow framework. It serves as an educational resource for designing deep learning architectures and implementing predictive models. The project provides ready-to-use examples for constructing neural network architectures and linear classifiers. It includes guides on performing tensor operations, automatic differentiation, and gradient descent optimization. The materials cover a range of machine learning capabilities, including the use of h

    Python
    View on GitHub↗4,492
Compare all 30 related projects→