While modern deep learning frameworks have revolutionized the ability for non-experts to train deep learning models, they have also democratized a host of other innovations which extend beyond the niche of deep learning. In this talk, I will explore some models and domains that are not commonly thought of as “machine learning” problems and show how PyTorch allows one to build more complex and scalable models than ever before. This represents an opportunity to revisit existing models, which I will do by showing how to implement them with PyTorch and integrate them into the rest of the PyData ecosystem.