This chapter focuses on how to productize a deep learning model. We use the word productize to define the creation of a software product from a deep learning model that can be used by other people and applications.
We are interested in models that use new data when it becomes available, continuously learning patterns from new data and, consequently, making better predictions. We study two strategies to deal with new data: one that re-trains an existing model, and another that creates a completely new model. Then, we implement the latter strategy in our Bitcoin prices prediction model so that it can continuously predict new Bitcoin prices.
This chapter also provides an exercise of how to deploy a model as a web application. By the end of this chapter, we will be able to deploy a working web-application (with a functioning HTTP API) and modify it to our heart&apos...
