This book is a beginner's guide to study machine learning, with focus on basic methods and algorithms. It aimed at senior undergraduates, graduate studentsand researchers in areas, such as computer science, bioinformatics, statistics and psychology. It is helpful for readers to be familiar with elementary calculus, linear algebra and probability before understanding the concepts and contents in this book. To make it easy to understand, we also provider basic mathematic reference in Appendix A and B.Our focus is on machine learning basics, models and also the recent trends. More specifically, we provide the most widely used mathematical models, derivation and optimization techniques. We intentionally avoid the experiments and evaluations because machine learning models are sensitive to various settings and datasets. Instead, this book is more like a tutorial of machine learning methods and algorithms, with the hope that readers can understand the basics and learn how to derive equations and optimize a given objective functions.

This means this book will mainly present methods and approaches to different machine learning problems. In addition, this book covers most machine learning topics, such as surprised learning, unsupervised learning and semi-supervised learning. Considering metrics playing a vital role to learn models, we start with similarity measures and build all topics based on these fundamentals. Most chapters will introduce a distinct family of machine learning models given different training inputs, with focus on understanding the models throughly. While we cannot reflect the most advances in machine learning, the mathematic methods and logics will lay solid foundations for readers to learn and handle more complex situations in different applications. We hope you enjoy and like the book.