Deep Learning is part of abroader family of machine learning methods based on artificial neural networks with representation learning. Deep learning architectures such as convolutional neural networks have been applied to fields including computer vision, machine vision, board games and much more, where they have produced results comparable to and in some cases surpassing human expert performance. In deep learning, a convolutional neural network(CNN, or ConvNet) is a class of deep neural networks, most commonly applied to analyzing visual imagery.
In this project, we trained a CNN to classify hand gestures into 3 classes (Rock, Paperor Scissors) and use it to play a game of RPS on an Android device. The game takes a snapshot of the player hand through the phone front camera, pass it to a server which runs pre processing and then classification on the image (using the CNN we trained) and pass the classification back to the player.