Skip to content

This project takes dataset from MNIST which contains (28 x 28) pixel images of 0-9 digits. I have trained a model which is an improvement of output softmax activation function. All the implemented layers are dense. Neural network contains 3 layers with 128,128 and 10 neurons respectively

srikarrao2003/HandWritten-DigitClassifier---Neural-Network-Project

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

16 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Handwritten DigitClassifier---Neural-Network-Project

This project takes dataset from MNIST which contains (28 x 28) pixel images of 0-9 digits. I have trained a model which is an improvement of output softmax activation function. All the implemented layers are dense. Neural network contains 3 layers with 128,128 and 10 neurons respectively

About

This project takes dataset from MNIST which contains (28 x 28) pixel images of 0-9 digits. I have trained a model which is an improvement of output softmax activation function. All the implemented layers are dense. Neural network contains 3 layers with 128,128 and 10 neurons respectively

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published