Machine learning has been one of the fastest growing fields over the last decade. Machines that can learn are becoming a part of our everyday lives. Machines that display intelligence and the ability to learn are powered by mathematics and algorithms. These topics do not have to be difficult. This book teaches a basic understanding of everything related to machine learning, so that beginner or intermediate level data scientists can expand their skills sets, and so that curious intellectuals can gain an understanding of the field.
This book provides a complete overview of machine learning. It builds on the information presented by its predecessor, Data Science in Layman’s Terms: Statistics. The book strikes a balance between an easy-reading tutorial and a theory intensive textbook, by first presenting the ideas, conceptually, at a high level, and then diving into the details and mathematics. Every chapter is accompanied by practical examples with Python, and R where applicable. The material in the first half of the book is arranged linearly, where each chapter builds on the knowledge of the previous chapters. The second half of the book explores subfields of machine learning, like natural language processing, computer vision, reinforcement learning, and network science.
Some of the practical applications you will learn from this book are how to:
- Construct a simulated agent that plays games without any instructions, and watch it learn to play on its own.
- Apply facial recognition to photos and videos in real time.
- Perform market basket analysis and clustering to improve marketing effectiveness or improve a customer’s shopping experience.
- Identify similar music, using sound alone.
- Generate realistic looking anime character faces.
- Identify abstract topics in text documents, and analyze how sentiment about different topics changes over time.
- Predict pairs of people who might soon connect in a social network, and explore how networks change over time.
- Convert scans or images of documents to text.
- Learn how to build neural networks with Keras, and how to probe them with TensorBoard to identify how they could be improved.
The GitHub repository accompanying this book can be found at: https: //github.com/nlinc1905/dsilt-ml-code
