Statistische Modelle

"Statistical Models in Artifical Intelligence"

The lectures and exercises will take place in the 1st block (18.10. - 29.11.2021).

 Beginn: 18.10.2021 Vorlesung 1 Montag 11 - 13 Uhr Online Prof. Dr. W. Schmid Vorlesung 2 Dienstag 14 - 16 Uhr Online Prof. Dr. W. Schmid Beginn: 20.10.2021 Übung 1 Mittwoch 09 - 11 Uhr GD 309 K. Gaykalov Übung 2 Mittwoch 11 - 13 Uhr GD 309 K. Gaykalov

Aim of the module (expected learning outcomes and competencies to be acquired):

Would you like to figure out what is hidden behind the Decision Tree? Do you feel lost in the Random Forests and need to Boost your spirit? Maybe, you are interesting what do the acronyms like LASSO, SVM, NN mean? Or, do you want to be in trend and get into the exciting area of Artificial Intelligence and Machine Learning? If so then you should consider visiting the course “Statistical Models in Artificial Intelligence”.

In the frame of the introductory courses in Statistics, we deal with summary statistics, develop the notion of probability, and finally turn to parametric models – mostly the normal – for inference. The student gets a fundamental insight into statistical thinking for data analysis.

But in recent years the underlying data sets are getting more and more complex and, in many cases, the problem is to analyze big and high-dimensional data sets. Such problems arise in many applications, e.g., E-commerce, internet text retrieval, self-driving vehicles, biomedical information, human-computer interaction, computer vision, etc. In order to overcome these problems, it is necessary that experts from computer science, engineering, and statistics closely work together. The main aim of this lecture is to give an introduction to statistical models in artificial intelligence. During lectures and tutorials, we discuss a wide spectrum of current machine learning algorithms. All presented methods will be accompanied with real-world examples and their implementations in R statistical software.

Inhalte des Moduls:

1) General Introduction

2) Linear Regression and its Cousins

3) Moving beyond linearity

4) Decision Trees

5) Random Forests and Boosting

6) Support Vector Machines

7) Neural Networks

Lehr- und Lernmethoden des Moduls:
Lectures and tutorials; use of practical examples, case study analysis, statistical data analysis.

Art der Prüfung/ Voraussetzung für die Vergabe von Leistungspunkten:
Oral exam

Further information: