Skip to content

Asad-Shahab/Micrograd

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MicroGrad

Backpropagation-based autograd engine

Overview

MicroGrad is an autograd engine that implements the core functionality of backpropagation for automatic differentiation. This project aims to provide a simplified version of the autograd mechanisms found in larger deep learning frameworks like PyTorch and TensorFlow.

Installation

  1. Clone this repository
  2. Install the required packages:
pip install micrograd

Tracing/Visualisation:

from micrograd import nn
n = nn.Neuron(2)
x = [Value(1.0), Value(-2.0)]
y = n(x)
dot = draw_dot(y)

Screenshot 2024-11-07 001645

About

Backpropagation-based autograd engine

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published