Skip to content

MNIST Digit Classifier : A project that trains a machine learning model using neural networks to recognize handwritten digits from the MNIST dataset. Includes data loading, preprocessing, training, and prediction with visualization support.

Notifications You must be signed in to change notification settings

ngusadeep/MNIST-digit-classifier

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

11 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MNIST classifier with Neural Networks

Overview

This project implements a handwritten digit recognition system using the MNIST dataset and a Neural Network built with TensorFlow and Keras Api.

The MNIST dataset contains 70,000 grayscale images of handwritten digits (0 to 9), each sized 28×28 pixels. In this project, we use a fully connected feedforward neural network (Multi-Layer Perceptron) to learn and classify digits.

The model is trained on 60,000 images and evaluated on 10,000 test images, demonstrating key concepts in:

  • Data preprocessing (reshaping, normalization)
  • Neural network architecture design
  • Model training using backpropagation and gradient descent
  • Evaluation metrics (accuracy, loss curves)
  • Making predictions on new handwritten digits

This project is a practical introduction to deep learning for image classification tasks.

About

MNIST Digit Classifier : A project that trains a machine learning model using neural networks to recognize handwritten digits from the MNIST dataset. Includes data loading, preprocessing, training, and prediction with visualization support.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published