Inspiration
In ECEN 250 my professor demonstrated how convulational neural networks often times can lead to more efficent and quicker training on images.
What it does
It runs four image tensors along with a palyer value and boost value into a PyTorch network
Challenges we ran into
Training the six different archtiectures and then having them compete took long computationaly.
What we learned
What's next for Case Close Neural Network
Implement a better loss function for game play which is les noisy.
Log in or sign up for Devpost to join the conversation.