Skip to content

Third, and last, project of the course FYS-STK4155, autumn 2018

Notifications You must be signed in to change notification settings

ingridut/NumpyCNN

 
 

Repository files navigation

Project 3 - Our first venture into Convolutional Neural Networks

This is the code written for the final project (#3) for the course FYS-STK4155, code by Betina, Ingrid, Polina, Mona and Henrik

Abstract:

In this project we study and attempt to make an comparison between our own NumPy-based CNN, Keras CNN, TensorFlow CNN and support vector machine model of MNIST database. We find that to make a computationally fast CNN is quite hard. However, prediction accuracy for NumPy-based CNN, Keras CNN,TensorFlow CNN and support vector machine models are 95.3%, 98.9%, 99.0% and 96.9%, respectively. Due to computational difficulties of NumPy-based CNN we had to resort to a smaller database of digits, 8 x 8 database, to obtain such a good accuracy. Another aspects that we could emphasize in case of NumPy-based, TensorFlow and Keras CNNs is that employed structure of CNN model and the training has an immense impact on the final prediction accuracy.

About

Third, and last, project of the course FYS-STK4155, autumn 2018

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 54.7%
  • Jupyter Notebook 45.3%