Description
Book SynopsisMachine learning without advanced math! This book presents a serious, practical look at machine learning, preparing you for valuable insights on your own data. The Art of Machine Learning is packed with real dataset examples and sophisticated advice on how to make full use of powerful machine learning methods. Readers will need only an intuitive grasp of charts, graphs, and the slope of a line, as well as familiarity with the R programming language. You'll become skilled in a range of machine learning methods, starting with the simple k-Nearest Neighbours method (k-NN), then on to random forests, gradient boosting, linear/logistic models, support vector machines, the LASSO, and neural networks. Final chapters introduce text and image classification, as well as time series. You'll learn not only how to use machine learning methods, but also why these methods work, providing the strong foundational background you'll need in practice. Additional features: How to avoid common problems, su
Trade Review"In contrast to other books about machine learning, there is a bigger emphasis on programming and usage in practice. In particular, there is an excellent explanation of how to avoid over/under-fitting, and how to use cross-validation. This book is sure to be helpful for students who are interested to understand the core concepts, as well as their practical implementations in R."
—Toby Dylan Hocking, Assistant Professor, Northern Arizona University"
The Art of Machine Learning by Norman Matloff is a welcome addition to a growing body of books about machine learning. Matloff, whose career spans both computer science and statistics, addresses the new and exciting field with a fresh approach."
—Dirk Eddelbuettel, Department of Statistics, University of IllinoisTable of ContentsAcknowledgments
IntroductionPART I: PROLOGUE, AND NEIGHBORHOOD-BASED METHODSChapter 1: Regression Models
Chapter 2: Classification Models
Chapter 3: Bias, Variance, Overfitting, and Cross-Validation
Chapter 4: Dealing with Large Numbers of Features
PART II: TREE-BASED METHODSChapter 5: A Step Beyond k-NN: Decision Trees
Chapter 6: Tweaking the Trees
Chapter 7: Finding a Good Set of Hyperparameters
PART III: METHODS BASED ON LINEAR RELATIONSHIPSChapter 8: Parametric Methods
Chapter 9: Cutting Things Down to Size: Regularization
PART IV: METHODS BASED ON SEPARATING LINES AND PLANESChapter 10: A Boundary Approach: Support Vector Machines
Chapter 11: Linear Models on Steroids: Neural Networks
PART V: APPLICATIONSChapter 12: Image Classification
Chapter 13: Handling Time Series and Text Data
Appendix A: List of Acronyms and Symbols
Appendix B: Statistics and ML Terminology Correspondence
Appendix C: Matrices, Data Frames, and Factor Conversions
Appendix D: Pitfall: Beware of “p-Hacking”!
