There are three distinct phases in the software-engineering process: conception, implementation, and deployment. This book has primarily focused on the implementation phase of the process, which is when a software engineer develops the core functionality (that is, a machine learning (ML) algorithm) and features of the project. In the last chapter, we discussed matters concerning the deployment phase. Our learning is nearly complete.
In this final chapter, we'll turn to the conception phase in order to round out our understanding of the full ML development process. Specifically, we'll discuss how to choose the best algorithm for a given problem. The ML ecosystem is evolving, intimidating, and full of jargon unfamiliar even to experienced software developers. I often see students of ML get stuck at the beginning of the process...