/Machine-learning-techniques-for-recognising-handwritten-digits

This project encompasses a range of neural and non-neural model implementations to classifiy MNIST digits. The goal is to compare the performance of each technique including details of hyper-parameters, training ans testing errors, training and testing duration and additional parameters used in the analysis.

Primary LanguageJupyter Notebook

Machine Learning techniques for recognising handwritten digits

This project encompasses a range of neural and non-neural model implementations to classifiy MNIST digits.

The goal is to compare the performance of each technique including details of hyper-parameters, training ans testing errors, training and testing duration and additional parameters used in the analysis.

Each of the techniques have been developed using Google Colaboratory therefore all required dependencies are included in the ipynb files.

Neural Techniques:

  • Convolutional Neural Network
  • Recurrent Neural Network
  • Deep Neural Network
  • Shallow Neural Network

Non-neural Techniques:

  • K-Nearest Neighbours
  • Support Vector Machine
  • Random Forest
  • Multinomial Logistic Regression

Authors: Victoria Porter, Will Holbrook, Laura Cope, Lauren Cooper, Joel Wolinsky and Oisin Tunney.