Skip to content

khnguyenn/DigitRecognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DigitRecognition

The Handwritten Digit Recognition is a project developed to classify digits drawn by the user in an interface.

he Training and Calculations of The Algorithm were implemented by Numpy Library.

The main objective of this project is to gain an in-depth understanding of how a neural network functions.

The Data Set

The Data Set : MNIST

How it works

Algorithm

The algorithm is a neural network with dense layers, following this configuration:

  • Input Size: 784
  • Hidden Layer 1: 50 neurons, activation function ReLU
  • Hidden Layer 2: 20 neurons, activation function ReLU
  • Output Layer: 10 neurons, activation function Softmax

Backpropagation: The batch gradient descent method was used with a batch size of 40 and 100 epochs, with a learning rate of 0.005.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors