Introduction

In previous chapters, we learned about various hardware and software infrastructures for AI practices. We learned about different databases and data solutions as well as their use cases. We learned about big data computing engines such as Spark, which allows engineers to process web-scale data. We also learned about using workflow management systems such as Airflow to manage data pipelines at scale. We also learned a lot about cloud data solutions and how to leverage cloud data storage and perform basic data-related tasks.

This chapter will focus on the science and the mathematical side of artificial intelligence. Without a proper understanding of the theory that underpins AI, we simply cannot build a robust AI application. If we can understand the math and science behind AI, then we will be able to apply different algorithms to solve different real-world problems. With the skills you will gain from this chapter, you will be able to innovate new AI algorithms to solve...