Skip to content

A simple handwritten digit recognition using Neural Networks,written in Python.

Notifications You must be signed in to change notification settings

golu360/Handwritten_Digit_Recognition_NN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

Handwritten_Digit_Recognition_NN

A simple handwritten digit recognition using Neural Networks,written in Python 3. To understand how Neural Networks work please refer to : http://neuralnetworksanddeeplearning.com/chap1.html

Dependencies used: NumPy Gzip Pickle.

Network.py contains all the source code about the implementation of Schocastic Gradient Desecent and the Network.

MNIST_Loader.py simply loads the MNIST Digit Data and splits it into test,validation and training data.

Deploy.py executes the recognition process,changes can be made to it accordingly.

Uses a 784 x 30 x 10 NN architecture,where 784 Input Neurons,30 Hidden Neurons and 10 output neurons(1 neuron for each digit (0-9)).

About

A simple handwritten digit recognition using Neural Networks,written in Python.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages