Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Digit-Recognizer

This project is a fulfillment to complete the Methods of Statistical Data Analysis postgraduate studies at AGH University of Science and Technology in Krakow, Poland.

In this project I compared several different Artificial Neural Network (ANN) architectures in terms of their accuracy in recognizing handwritten digits. The best performing neural network scored 99.6% accuracy on MNIST dataset which, when the model was submitted, was among the top 10% accuracies on Kaggle.

Kaggle Score

About

MNIST digit recognizer for Kaggle competition

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages