A tiny deep learning library written in Java
High-performance Machine Learning, Dynamic Auto-Differentiation and Tensor Algebra crate for Rust
A Lightweight Deep Neural Network Library only using NumPy that offers Pytorch-like API
DeepTensor: A minimal PyTorch-like deep learning library focused on custom autograd and efficient tensor operations.
A pure-Python, zero-dependency tensor and autograd library, a mini NumPy + PyTorch built from scratch.
This is a minimal, from-scratch implementation of a scalar-valued automatic differentiation (autograd) engine and a small neural network library built on top of it. It follows the ideas behind Andrej Karpathy's micrograd, rebuilt line by line to actually understand how backpropagation works — not just call it.
A TypeScript implementation of an autograd engine for educational purposes.
A simple Autodiff with Dynamic Computational Graph compatible with numpy. For educational purposes. Made by me, SaruboDev, a junior Data Scientist/AI Researcher
A minimalist, CUDA-native deep learning library featuring a custom autograd system and a PyTorch-inspired API, built to explore framework internals and GPU-accelerated computing.
A small autograd engine with backpropagation (reverse-mode autodiff) over a dynamically built directed acyclic graph (DAG) and a small neural networks library on top of it following a PyTorch-like API.
Autograd: is a lightweight Python engine for automatic differentiation and neural networks, providing a clear, educational implementation of backpropagation and computational graphs.
Tiny autograd engine written in Go.
🚀 Official Executive Portfolio of Eunho Kim (@uno-km) · Enterprise Java/Spring Boot & PostgreSQL Tech Lead, AMEVA Edge-AI Ecosystem Creator, WebGPU Autograd, and MCP Systems Architect.
A reverse-mode automatic differentiation engine built from scratch in C++
ML systems platform for distributed training, transformer inference, profiling, benchmarking, observability, and model serving.
Noise2Noise is an AI denoiser trained with noisy images only. We implemented a ligther version which trains faster on smaller pictures without losing performance and an even simpler one where every low-level component was implemented from scratch, including a reimplementation of autograd.
A minimal scalar-valued autograd engine and neural network library inspired by Andrej Karpathy's backpropagation lecture.
Micro-Grad: Simple neural network and autograd engine written from scratch in Python.
To associate your repository with the autograd-engine topic, visit your repo's landing page and select "manage topics."