Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Applied Supervised Learning with R

You're reading from   Applied Supervised Learning with R Use machine learning libraries of R to build models that solve business problems and predict future trends

Arrow left icon
Product type Paperback
Published in May 2019
Publisher
ISBN-13 9781838556334
Length 502 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (2):
Arrow left icon
Jojo Moolayil Jojo Moolayil
Author Profile Icon Jojo Moolayil
Jojo Moolayil
Karthik Ramasubramanian Karthik Ramasubramanian
Author Profile Icon Karthik Ramasubramanian
Karthik Ramasubramanian
Arrow right icon
View More author details
Toc

Table of Contents (12) Chapters Close

Applied Supervised Learning with R
Preface
1. R for Advanced Analytics FREE CHAPTER 2. Exploratory Analysis of Data 3. Introduction to Supervised Learning 4. Regression 5. Classification 6. Feature Selection and Dimensionality Reduction 7. Model Improvements 8. Model Deployment 9. Capstone Project - Based on Research Papers Appendix

Random Search Optimization


In random search optimization, we overcome one of the disadvantages of grid search optimization, which is choosing the best set of optimal values within the candidate values for each hyperparameter in the grid. Here, we opt for random choices from a distribution (in case of a continuous value for hyperparameters), instead of a static list that we would define. In random search optimization, we have a wider gamut of options to search from, as the continuous values for a hyperparameter are chosen randomly from a distribution. This increases the chances of finding the best value for a hyperparameter to a great extent.

Some of us might have already started understanding how random choices can always have the possibility of incorporating the best values for a hyperparameter. The true answer is that it doesn't always have an absolute advantage over grid search, but with a fairly large number of iterations, the chances of finding a more optimal set of hyperparameter increases...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime