
As an Amazon Associate and affiliate partner, Menrva Books earns from qualifying purchases. Learn more
This book provides a gentle introduction to the field of machine learning. It is intended for beginners in the field. The book gives an overview of the main branches of machine learning, namely supervised and unsupervised learning, regression, and dimensionality reduction. Topics are treated in a simplified pedagogic manner, and most sections include concise summaries. The book covers a large number of classifiers. These are derived mathematically in the simplest way possible, and their characteristics are summarized highlighting the strengths and weaknesses of each. Topics such as the curse of dimensionality, classifier complexity, the bias-variance trade-off, multiple instance learning, and one-class classification are also presented. Under unsupervised learning, many clustering techniques are outlined and algorithms are visualized while emphasizing the shortcomings of each. Selected topics are chosen in regression including kernel smoothers, ridge and LASSO regression. The chapter on dimensionality reduction covers several feature extraction and feature selection methods including branch and bound and genetic algorithms. The book assumes no prior knowledge of machine learning on the part of the reader. Basic knowledge of some topics in mathematics such as linear algebra and probability theory are provided in the appendices.
This book offers a simplified pedagogical introduction to the fundamental concepts and techniques of machine learning. The author, Jimmy Azar, assumes no prior knowledge of the subject, aiming to guide beginners through the main branches of machine learning, including supervised and unsupervised learning, regression, and dimensionality reduction. The text prioritizes a clear, mathematical derivation of classifiers, highlighting their strengths and weaknesses, and addresses key theoretical concepts such as the curse of dimensionality and the bias-variance trade-off.
The book is designed as an accessible entry point into machine learning for novices, focusing on simplified explanations and pedagogical approaches. Its structure, including concise summaries and mathematical derivations presented in a straightforward manner, suggests a text aimed at building foundational understanding. The inclusion of appendices for prerequisite mathematical knowledge further indicates an intention to cater to readers without extensive prior exposure to the field. The scope covers core areas like supervised and unsupervised learning, regression, and dimensionality reduction, positioning it as a comprehensive introductory resource.
Page Count:
204
Publication Date:
2018-03-27
Publisher:
CreateSpace Independent Publishing Platform
ISBN-10:
1986853586
ISBN-13:
9781986853583
No comments yet. Be the first to share your thoughts!