Backpropagation Python Packages

autograd

Efficiently computes derivatives of NumPy code.

pyrddlgym-jax

JAX compilation of RDDL description files, and a differentiable planner in JAX.

ntk-ml

A from-scratch neural network and tensor library built in Python for learning, experimentation, and deep understanding of modern ML systems.

weed-loader

Minimalist AI/ML inference and backprogation in the style of Qrack

weed-loader-cpu

Minimalist AI/ML inference and backprogation in the style of Qrack

odtbrain

Python library for diffraction tomography with the Born and Rytov approximations

nanograd-lite

A minimal NumPy-based autograd engine and neural network library, built from scratch

synapgrad

A lightweight autograd engine with a deep learning library and a Torch-like API

dlfs

Implementation from scratch (using numpy arrays) of a framework based on keras interface which allows to build and train Fully Connected Networks and Convolutional Neural Networks (CNNs).

synapx

A deep learning library powered by a C++ autograd engine, featuring a PyTorch-like API and cross-platform support.

npnet

Build neural networks based only on Numpy

pileoffeather

Lightweight and easy to use ml library for small projects, create a neural network in minutes.

freegrad

A PyTorch extension for experimenting with alternative gradient flows.

tonygrad

A tiny scalar-valued autograd engine with a small PyTorch-like neural network library on top.

randomized-based-feedforward-neural-network

Package for feedforward neural network with randomized-based algorithms

autograd-latest

Efficiently computes derivatives of numpy code.

pocketgrad

A lightweight autograd engine and neural network library

symple

Simple Automatic Differentiation in Python

minitf

Simplified version of Tensorflow for learning purposes.

sympyle

Automatic differentiation in python