Skip to content

Neural network recognizing handwritten digits, trained on the MNIST dataset.

Notifications You must be signed in to change notification settings

wczyz/Digit-Recognizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Digit-Recognizer

This is a neural network that recognizes handwritten digits from the MNIST dataset. It consists of 3 fully-connected layers and is trained using online gradient descent.

With 200 neurons in the hidden layer and 5 epochs it achieves about 96.5% accuracy rate on the test dataset.

For the gradient descent algorithm to execute in a reasonable time, this version has 30 neurons in the hidden layer and the iteration goes on only through 1 epoch.

It achieves about 92% accuracy.

About

Neural network recognizing handwritten digits, trained on the MNIST dataset.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages