/MNIST-Digit-recognition

Utilizing various CNN architectures to perform digit recognition on the MNIST Dataset.

Primary LanguageJupyter Notebook

MNIST Digit Recognition Using Various CNN Architectures

In this project, I have explored different Convolutional Neural Network (CNN) architectures to perform digit recognition on the MNIST dataset. The goal is to compare the performances of these architectures in accurately classifying handwritten digits.

The CNN architectures used are as follows:

  • MLP (Multi-Layer Perceptron): A classic fully connected neural network architecture.
  • LeNet-5: A pioneering CNN architecture developed by Yann LeCun for handwritten digit recognition.
  • VGG (Visual Geometry Group): A deep CNN architecture known for its simplicity and effectiveness in image classification tasks.
  • ResNet (Residual Neural Network): A deep CNN architecture that introduced residual connections to facilitate training of extremely deep networks.