Introduction to Machine Learning with R

The course will cover a number of methods for both prediction and classification problems using both supervised and unsupervised machine-learning techniques in R.

This is an intermediate course for those who have either completed an ‘Introduction to R - Data Analysis and Programming’ course or who have equivalent experience using R.

R makes the implementation of advanced machine learning techniques a relatively straight forward process – during the course, your will learn how to harness these techniques to address problems such as house price prediction, customer segmentation and election result prediction.

Supervised learning

• Classification (e.g. predicting whether a passenger will survive or die on the titanic based on demographic information): Decision trees, logistic regression
• Numeric prediction (e.g. what is the correct value of a house): Regression trees, linear regression

Unsupervised learning

• Pattern discovery (e.g. which items are commonly bought together): Association rules
• Clustering (finding distinct groups in data e.g. groups of individuals with similar shopping behaviour): K-means clustering 

We will apply these techniques to a variety or real-world datasets, such as house price data, financial data and demographic data. You will also be encouraged to source your own datasets to test your skills.

This course will take a practical approach; we will prioritise getting used to applying machine-learning techniques to data and interpreting results, rather than focusing on theoretical points. However, we will point you towards online content to help you with the theoretical side and prepare you for future learning in the field.

By the end of the course, you will have built a library of re-usable code and an understanding of how to solve common problems and where to look for useful guidance. This will help you in your future learning and implementation of machine learning techniques.

Prerequisites:

• Some basic experience with R
• Conducting simple statistical analyses (e.g. obtaining means, medians and standard deviations)
• BYO (Bring Your Own) Dataset - optional

Tutoring

The course is directed by Dr Will Lawrence, who completed his PhD at the Department of Electronics and Computer Science at the University of Southampton, and who has a background in psychology. Will has rich experience in delivering training in both Python and R, to diverse audiences.

Discounts

• 10% when a participant enrolls for more than one of our courses (at the same time)
• 20% UK students
• 25% UK Law & Society Association (UKLSA) Members
• If five people register from the same institution for the same intake, the fifth place is free
• Goldsmiths students, staff and alumni - email us for current discounts

As a University, we are able to offer our courses at minimum prices, and free of VAT - to make knowledge available to as wide audience as possible.

FAQs

How can I contact the organiser with any questions?

For any further enquiries or to receive the code to qualify for a discount, please contact at us at air (@gold.ac.uk), or alternatively, 020 7078 5468.

Refund policy: See AIR courses main page

Fees

£495  

Booking information

Enquiries

If you have any questions about this course please contact air (@gold.ac.uk) or call +44 (0)20 7078 5468.

For information on our upcoming short courses please sign up to our mailing list.

Location

Goldsmiths, University of London