Skip to content

didjunho/mnistNeuralNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

mnistNeuralNet

implemented neural network to classify handwritten digits between 0-9

trained with MNIST database (30,000 inputs)

learning rate optimized through validation set, early stopping done through validation set (3,000 inputs)

runs for 100 epochs and testing set hits 95%+~ accuracy (300 inputs)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages