For the final project, you have two options.
In this project, you will solve a supervised learning problem for a machine learning competition from Kaggle. This project option gives you lots of freedom to choose what data set you will work with and what algorithms you will use.
The full description of this project option can be found here: Kaggle Competition Project
For this project, you will replicate one of the variants of AlphaGo, combining Monte Carlo tree search and deep reinforcement learning to play Hex. This project option gives you the chance to bring together the things we have learned about reinforcement learning, neural networks, and game playing.
The full description of this project option can be found here: AlphaHex Project
For either project, you will describe your results in the LaTex file project.tex. This file already contains a basic structure that you should follow. Feel free to change the section headings, or to add additional sections. Recall that you use pdflatex to convert the LaTex into a pdf file. As you work, be sure to take notes on what you tried and save some of your intermediate models so that you have something to test against in the experiments section of your paper.