In this book, we are rarely concerned with the algorithmic details of how models are constructed, or how they’re structured. Algorithms are tasty morsels of thought that are ultimately expressed in code and hopefully fade into the background because they just work, which was, after all, the point. The most exciting algorithmic development of last year is the mundane executable of next year. Instead, we are overwhelmingly interested in two things: the data used to construct the models, and the processing pipeline that takes the data and transforms it into models.
نظرات کاربران