Skip to content

agarwalgaurav811/Handwritten-Digit-classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Handwritten-Digit-classifier

This is the implementation of a multilayer neural network. Done in python and numpy with no external machine learning framework used. NN gives accuracy upto 95-96%. The purpose of this project was to understand the full architecture of a neural network and to visually break down what's going on while training to recognize handwritten digits.

Setting up:

git clone https://github.com/agarwalgaurav811/Handwritten-Digit-classifier.git
cd Handwritten-Digit-classifier/
python network.py

About

Handwritten digit recognition system trained on MNIST data.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages