CNN-Image-Classification

This repository contains the implementation of a Convolutional Neural Network (CNN) architecture applied to the task of image classification using the canonical CIFAR-10 dataset. The analysis is broken into two parts:

1. Discussing and understanding the importance of Dropout in a Convolutional Neural Network to provide model regularization
2. Implementing a version of SimpleNet, originally created by Hasanpour et al. (2018). The aim here is to achieve performance close to state-of-the-art with a much less computationally intensive architecture, one that can be run on 1 GPU in Google Colab.