The world of deep learning has traditionally been an academic world, drawing from mathematics, statistics, and operations research. This has meant great advances in the development of theory and algorithms, but software engineering best practices have sometimes been left behind. In this talk, the creator of fastai will explain how bringing software engineering best practices, such as layered API design and decoupling, have allowed him to provide a deep learning library that is both easier to use for beginners, at the same time as being more deeply hackable for experts, and also increasing performance. He will be drawing from research discussed in the peer reviewed paper describing the principles of fastai.
