By opening this book, you are taking the first step in disrupting your own knowledge by approaching solutions to complex problems with machine learning. You will be achieving this with the use of Microsoft's ML.NET framework. Having spent several years applying machine learning to cybersecurity, I'm confident that the knowledge you garner from this book will not only open career opportunities to you but also open up your thought processes and change the way you approach problems. No longer will you even approach a complex problem without thinking about how machine learning could possibly solve it.
Over the course of this book, you will learn about the following:
- How and when to use five different algorithms that ML.NET provides
- Real-world end-to-end examples demonstrating ML.NET algorithms
- Best practices when training your models, building your training sets, and feature engineering
- Using pre-trained models in both TensorFlow and ONNX formats
This book does assume that you have a reasonably solid understanding of C#. If you have other experience with a strongly typed object-oriented programming language such as C++ or Java, the syntax and design patterns are similar enough to not hinder your ability to follow the book. However, if this is your first deep dive into a strongly typed language such as C#, I strongly suggest picking up Learn C# in 7 Days, by Gaurav Aroraa, published by Packt Publishing, to get a quick foundation. In addition, no prior machine learning experience is required or expected, although a cursory understanding will accelerate your learning.
In this chapter, we will cover the following:
- The importance of learning about machine learning today
- The model-building process
- Exploring types of learning
- Exploring various machine learning algorithms
- Introduction to ML.NET
By the end of the chapter, you should have a fundamental understanding of what it takes to build a model from start to finish, providing the basis for the remainder of the book.
