Beating Roulette

This my project for senior design I and II and Purdue that spans two semesters and is a full year. My groups goal was to "Beat the game of Roulette" and thus we set out to develop/design a neural network to object identify the ball and roulette wheel and draw a prediction as to where it would land. Of course, per artificial neural network standards, nothing would be hardcoded and we would "train" the network (via thousands of large datasets) to "learn" the correct answer. You can view a sample to the right of this text by clicking on the youtube video link.

If you would like to view the source code, please click here to go to my github repository. Please read the README.md file at the bottom of the repository if you plan to install the network or if you simply want to learn more about the steps we took to develop this network. Github Source