Introduction to Machine Learning

Summary

This chapter traces the modern origins of machine learning (ML) and outlines some of its key milestones. ML creates specific types of computer programs that mimic the way humans learn to gradually improve their performance. In general, there are three types of ML: supervised learning, unsupervised learning, and semi‐supervised learning. Unlike statistical methods, ML adaptively learns from its experiences. In fact, one of the major advantages of ML over traditional statistical methods is its ability to derive a relationship(s) between inputs and outputs without assuming prior forms or existing relationships. Collectively, computational methods can be divided into soft computing and hard computing. Hard computing methods are those that integrate a high degree of certainty into solving problems, while their soft computing counterparts are done via approximate means. ML falls under the latter. The chapter covers the complete process of developing and creating ML models from a civil and environmental engineering perspective.