I am asking for a book reference to further my studies in machine learning with the R programming language. Feel free to reference multiple books that are just machine learning or just R programming. I understand some basic concepts, but I think I am having trouble applying my knowledge to get real results.
For example, I would like to test my knowledge out with some exercises from real datasets. Questions I would like to answer are: How much more accuracy can I gain by fine-tuning a regularization parameter? What is a good accuracy for a particular problem (in practice, what is the intuitive feel)? What are some common methods to improve my accuracy w.r.t features? How do I find the best value for a regularization parameter? Which machine learning algorithm will work well for this problem?
My programming knowledge of R is the basic control structures and some of the functional features such as the
apply function to iterate over a data-frame. I also know some basics of the data-frame data structure and the list data structure.
I can apply a bunch of machine learning algorithms with R, but I do not know enough to tackle a wide variety of problems. I am hoping to gain some practical experience from book exercises as well as good understandings of the main algorithms. I understand math (calculus, graph theory, and probability) but I probably need a refresher in certain areas.
- In summary, what book would you recommend for someone interested in gaining practical knowledge in Machine Learning and using the R programming language?