Skip to content

Experiments with Neural Network in Handwritten Digits Classification with MNIST data

Notifications You must be signed in to change notification settings

dothanhdatle/Deep-learning-test-on-MNIST-data

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Deep-learning-MNIST-Handwritten-Digits-Classification

Experiments with Neural Network in Handwritten Digits Classification with MNIST data:

  • Simple Neural network with 1 hidden layer
  • Neural network with 2 hidden layers with 2 activation functions: ReLU, Tanh
  • Neural network with batch normalization
  • Neural network with He weights initialisation for ReLU activation
  • Neural network with dropout to reduce overfitting.

About

Experiments with Neural Network in Handwritten Digits Classification with MNIST data

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published