Artificial intelligence (AI) and machine learning (ML) are rapidly growing fields, drawing great interest among students. Many students in a range of fields, including mathematics, computer science, statistics, data science, and more, see AI and ML as the keys to their futures.
Mathematics for Artificial Intelligence provides the basic mathematics needed to understand AI and ML. It serves both students of mathematics and those who want to fill any gaps in their mathematics experience. It is written as both a text for a course and as a focused look at mathematics needed for readers hoping to learn more.
The author has taught every topic in this book, often in different contexts, and the material and exercises are drawn from lecture notes. The material in the book represents a curated set of topics from the undergraduate math curriculum, some first-year seminar material, and some student project topics. Through carefully chosen examples and discussion in the text, the reader will learn how and where these tools are applied. AI and ML connections are raised along the way.
It presumes the reader has at least completed the traditional three-semester calculus course. Linear algebra is presented as needed and should not require a completed course. The book is also well-suited for self-paced learning. Each chapter can be read independently with the help of the index for cross-referencing. Exercises are included.