A lot of recent progress has been made towards developing computer vision systems that translate sign language to spoken language. This technology often relies on complex neural network architectures that can detect subtle patterns in streaming video. However, as a first step, towards understanding how to build a translation system, we can reduce the size of the problem by translating individual letters, instead of sentences. We will train a convolutional neural network to classify images of American Sign Language (ASL) letters. After loading, examining, and preprocessing the data, we will train the network and test its performance. View the original project on GitHub