|
Instructors: Prof. Dr. Ole Wilms
Event type:
Lecture + practical course
Displayed in timetable as:
Hours per week:
3
Credits:
6,0
Language of instruction:
English
Min. | Max. participants:
- | 81
Comments/contents:
This bachelor level course will give an introduction to machine learning techniques with a particular focus on how they can be applied in practice. You will learn why, when, and how to apply Big Data methodology to real-world problems. For this, we will review the most common supervised and unsupervised machine learning techniques and learn how they can be implemented in practice. A large focus of the course will be on applications. So you will learn how to work with large datasets using the software package R, apply the appropriate machine learning algorithms and interpret the outcomes.
Covered topics:
- Introduction to statistical computing. Students will learn basics about using computers to analyze big data, with a special emphasis on R, and the most common big data libraries in R.
- Working with data. Data is rarely found in perfectly usable form. You will learn how to clean the data to make it usable.
- Supervised learning techniques have become very advanced. We cover basic regression and classification techniques, as well as more advanced methods such as decision trees, support vector machines, and boosting.
- If time permits, we will cover the basics of deep learning and unsupervised learning.
- We will discuss the risks of overfitting. Big Data allows fitting very flexible models, which permits learning subtle features of the data. This creates the danger of overfitting, where the fit fails out of sample. Controlling overfitting is one of the central tasks in the analysis of Big Data.
- For all topics of the course the focus will be on applications. So each lecture will be accompanied by computer labs where you learn how to implement the course material in R.
Learning objectives:
Upon completion of the course, you should be able to:
- Use the free software R to solve key tasks in big data including loading and cleaning big datasets, using libraries/r-packages and summarize and visualize data.
- Apply supervised learning techniques to analyze economic and financial data and make predictions.
- Analyze the main benefits and limitations of supervised and unsupervised learning methods we cover in class.
- Evaluate and compare the performance of different methods.
Didactic concept:
Lectures take place on campus, Tuesday from 14.00-16.30. During these sessions, we will not only cover the course content, but also apply the course material using the software R. Hence, ideally you bring a laptop to class but it is also possible to redo the exercises later at home if you don’t have a laptop.
In the beginning of the course, there will be an introductory programming session. In this session you will learn basic programming skills using the software package R as well as how to handle data in R. If you are already familiar with R, you can skip this session.
All course materials will be made available on OpenOlat.
Literature:
The course is build around the textbook "An Introduction to Statistical Learning with Applications in R" by James, Witten, Hastie and Tibshirani. The book as well as datasets and practice exercises are available at https://statlearning.com/
Additional examination information:
The final grade will be based on the take home exam. In this exam you will be asked to solve machine learning problems on your home computer and submit a short report. The course will include several problem sets in which you learn how to apply the machine learning techniques. These exercises will prepare you well for the take home exam.
TAKE-HOME EXAM:
Time to process the exam: 240 minutes
Time frame in which the exam can be completed:
First exam: 28 July 2023, 8:00 am-11:59 pm
Second exam: 22 September 2023, 8:00 am-11:59 pm
The examiner will provide information about the hand out of exam tasks and their submission.
|
