Image Classification on the MNIST Handwritten Digits Recognition Dataset

This repository contains a deep learning project focused on image classification using the MNIST handwritten digits recognition dataset.

The related notebook can be found here

Dataset

• MNIST Dataset The MNIST dataset is a benchmark dataset in machine learning and computer vision. It consists of 60,000 grayscale images of handwritten digits (0-9) for training and 10,000 images for testing. Each image has a resolution of 28x28 pixels.

To access the MNIST dataset, you can refer to the following link: MNIST Dataset

Modelling

• Model A: Fully Connected Layers

• Model B: Convolutional Neural Network (CNN)

• Pre-Trained Network: EfficientNetB3

• State-of-the-Art Classifier Design on the MNIST dataset