Skip to content

Simple Neural Network for MNIST handwritten digits recognition

Notifications You must be signed in to change notification settings

lynngao/NeuralNetwork

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

NeuralNetwork

Simple Neural Network for MNIST handwritten digits recognition

Please download data from here and follow the instructions to get training and test data: http://deeplearning.net/tutorial/gettingstarted.html

Two fully connected hidden layers with ReLu and softmax activation functions (ReLu performs much better than sigmoid)

Use Xavier initialization for weights and bias initialization

First layer with 128 neurons and second with 32 layers

Batch size = 128 and number of epoches used is depend on training data size (20 is enough for most of sizes)

Achieves accuracy as high as 97% for test data

About

Simple Neural Network for MNIST handwritten digits recognition

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages