The goal of this chapter is to take you through the Machine learning landscape and lay out the basic concepts upfront for the chapters that follow. More importantly, the focus is to help you explore various learning strategies and take a deep dive into the different subfields of Machine learning. The techniques and algorithms under each subfield, and the overall architecture that forms the core for any Machine learning project implementation, are covered in depth.
There are many publications on Machine learning, and a lot of work has been done in past in this field. Further to the concepts of Machine learning, the focus will be primarily on specific practical implementation aspects through real-world examples. It is important that you already have a relatively high degree of knowledge in basic programming techniques and algorithmic paradigms; although for every programming section, the required primers are in place.
The following topics listed are covered in depth in this chapter:
Introduction to Machine learning
A basic definition and the usage context
The differences and similarities between Machine learning and data mining, Artificial Intelligence (AI), statistics, and data science
The relationship with big data
The terminology and mechanics: model, accuracy, data, features, complexity, and evaluation measures
Machine learning subfields: supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning, and deep learning. Specific Machine learning techniques and algorithms are also covered under each of the machine learning subfields
Machine learning problem categories: Classification, Regression, Forecasting, and Optimization
Machine learning architecture, process lifecycle, and practical problems
Machine learning technologies, tools, and frameworks