Skip to content

Trains neural network to recognize handwritten digits with only Numpy

License

Notifications You must be signed in to change notification settings

JonathanCen/mnist-neural-network

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MNIST Neural Network 🔢

MNIST Neural Network is a python application that trains a neural network on the MNIST dataset to recognize handwritten digits WITHOUT using any machine learning libraries (only NumPy). The neural network contains only one fully connected layer with 1024 neurons with ReLU activation function and an output layer with softmax activation function, and the model is trained using the cross-entropy loss function. This is one of two parts of the interactive web application, which you can test out: Live Demo.

Getting Started

These instructions will give you a copy of the neural network up and running on your local machine for development and testing purposes.

Prerequisites

To run this application locally on your computer, you'll need Git and Python installed on your computer.

Installing

Then run the following command in the command line and go to the desired directory to store this project:

Clone this repository:

git clone https://github.com/JonathanCen/mnist-neural-network.git

Start running the neural network:

python3 main

Built With

  • NumPy - Used to for all the matrix computations/manipulated

Contributing

All issues and feature requests are welcome. Feel free to check the issues page if you want to contribute.

Authors

License

Copyright © 2019 Jonathan Cen.
This project is MIT licensed.

About

Trains neural network to recognize handwritten digits with only Numpy

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages