https://github.com/nachiket273/micrograd_rs

A Beginner's implementation of Andrej karpathy's micrograd in Rust.
https://github.com/nachiket273/micrograd_rs

micrograd mlp neural-networks relu rust study-project

Last synced: about 19 hours ago
JSON representation

A Beginner's implementation of Andrej karpathy's micrograd in Rust.

• Host: GitHub
• URL: https://github.com/nachiket273/micrograd_rs
• Owner: nachiket273
• License: mit
• Created: 2024-08-28T20:28:45.000Z (2 months ago)
• Default Branch: main
• Last Pushed: 2024-09-19T18:35:29.000Z (about 2 months ago)
• Last Synced: 2024-10-31T11:48:50.890Z (6 days ago)
• Topics: micrograd, mlp, neural-networks, relu, rust, study-project
• Language: Rust
• Homepage:
• Size: 33.2 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# micrograd_rs

[![Crate](https://img.shields.io/crates/v/micrograd_rs_nt.svg)](https://crates.io/crates/micrograd_rs_nt)




A Rust Beginner's implementation of [Andrej karpathy's micrograd](https://github.com/karpathy/micrograd). 


Here's [Link](https://www.youtube.com/watch?v=VMj-3S1tku0) to the YouTube video. 


Also thanks to [micrograd-rust](https://github.com/sloganking/micrograd-rust) for reference implementation in rust.




## The current implementation is limited to:


==============================================


* scalar valued autograd

* Implementation of forward and backward pass for arithmetic operations and power operation.

* Implementation of forward and backward pass for activation functions - tanh and relu.




## Sample Output: 


===============================================


![Sample Training Output for MLP](./img/train.png)




## TO-DO:

==========================================

* graph visulization using libraries like [graphviz](https://graphviz.org/download/)

* Implementation of Tensor type library from scratch

* Improve implementation of MLP, activations etc for Tensors.