The landscape for AI platforms and methods is diverse; in this chapter, we've outlined some of the most promising and well regarded technologies in the AI arena. For deep learning packages, we learned about TensorFlow, PyTorch, and Keras. TensorFlow, released by Google, is the most popular and robust of the deep learning libraries. It utilizes sessions and static graphs to compile to its underlying C++ code. PyTorch, on the other hand, is a newer library that features a dynamic graph for runtime execution, which allows it to feel like native Python. Lastly, Keras is a high-level library that runs on top of TensorFlow, and can be useful for creating straightforward networks where customization is not needed.
We also discussed cloud computing, utilizing AWS as the most popular cloud computing service, with its primary workhorses being the EC2 instance and the s3 Bucket...
