## Introduction & Motivation
Welcome to the Project 5 competition for CS486: Artificial Intelligence, AY24-1. Throughout this competition, you will be designing and training a neural network in PyTorch that predicts the presence of retinal disease from optical coherence tomography (OCT) images. See below for detailed instructions, and good luck!

Using the training/validation/test datasets and the optional starter notebook provided here, your task is to design a network that achieves or surpasses a baseline accuracy when predicting one of four classes from a given OCT image: Choroidal Neovascularization, Diabetic Macular Edema, Drusen, and Normal. Beyond meeting this baseline, more robust and better designed networks will earn you a higher position on the competition leaderboard.

As the deep learning engineer, it is not important for you to understand exactly how OCT images are obtained, nor do you need to understand the medical conditions your network predicts (however, if you want to know more about these topics, check the Acknowledgements). In the real world, you would ideally seek the counsel of optometrists and other subject matter experts to design a network that best suits their needs. For this project, your focus should remain squarely on designing the best network possible, given the data provided.

## Where Do I Begin?

Download the starter notebook and training/validation/test datasets from the 'Data' tab. You can expect the starter notebook to assist you with preprocessing the data and generation of your results for submission to the competition leaderboard. Your job is to provide the code required to define your network (number of neurons, number of hidden layers, activation functions, etc.) and train it.

Note that the starter notebook provides only the baseline amount of preprocessing required. Many preprocessing techniques exist that could improve your results (see data augmentation, batch normalization, etc.), but these methods are outside the scope of the course. Similarly, alternative network architectures (e.g. convolutional neural networks) are far better suited for datasets containing images, but you will not be explicitly taught how to create these in class. Adventurous students who explore what is possible beyond what you see in class will certainly achieve higher leaderboard positions, though this is not required to receive max points on this project.

Refer to the Submission, Timeline, and Acknowledgements tabs on the left for further details about the competition.