Free PDF Download
In Machine Learning, This book examines machine learning from an angle known as model-based machine learning. This perspective will guide you to create successful machine learning solutions without forcing you to master a large amount of machine learning documentation.
Model-Based Machine Learning Introduction
In this book, we look at machine learning from a new angle that we call model-driven machine learning. This perspective helps to solve all these challenges and makes the process of creating effective machine learning solutions much more systematic. It applies to the entire spectrum of machine learning techniques and application domains, and will guide you through building successful machine learning solutions without requiring you to master huge machine learning documents.
Who is this book for?
This book is quite unusual for a machine learning textbook in that we don’t go through dozens of different algorithms. Instead, we introduce all the key ideas through a series of case studies related to real-world applications. Case studies are central because only in an applied context does it make sense to discuss modeling assumptions. Therefore, each program presents a case study drawn from a real-world application that has been addressed by a model-driven approach. The Exception is the first chapter that explores a simple fictional matter involving a murder mystery.
Each chapter also introduces various machine learning concepts, not abstract ideas, but concrete techniques driven by the needs of the application. You can consider these concepts as the basis for building models. Although you will need to invest time to fully understand these concepts, you will soon discover that a lot of models can be built from a relatively small number of building blocks. By going through the case studies in this book, you will learn how to use these components, and hopefully you will have a sufficient appreciation for the power and versatility of the model-based approach to solve machine learning problems.