Book: Practical Machine Learning with R

Per request from Packt Publishing, I wrote two chapters for the book Practical Machine Learning with R: Define, build, and evaluate machine learning models for real-world applications.

I contributed chapter 4 (Introduction to neuralnet and Evaluation Methods) and chapter 5 (Linear and Logistic Regression Models).

In chapter 4, students/readers train simple neural networks with the neuralnet package and use cross-validation to select between models.

In chapter 5, students fit linear and logistic regression models and attempt to interpret them. They use cross-validation to select between model formulas, create baseline evaluations for the task at hand, and use Pareto dominance when multiple evaluation metrics disagree.

The book was written as a two-day course and contains a lot of exercises. Obviously, a two-day course only scratches the surface, but I believe the book is a good practical introduction – a kind of “hands-on overview”.

The process of writing and editing, working with editors, etc., has been very educational for me. It’s taken a lot of time and energy, but writing two chapters is definitely a good first peak at that kind of work.




Date: september 2019
Skills: Programming, R
Client: Packt Publishing