Explainability and Variable Selection in Learning (Sommersemester 2020)

Lecturer: Prof. Dr. Bernhard Renard (Data Analytics and Computational Statistics) , Tom Altenburg (Data Analytics and Computational Statistics)

General Information

• Weekly Hours: 2
• Credits: 3
• Graded: yes
• Enrolment Deadline: 06.04.2020 - 22.04.2020
• Teaching Form: Seminar
• Enrolment Type: Compulsory Module
• Course Language: English
• Maximum number of participants: 10

Programs, Module Groups & Modules

Description

With machine learning being increasingly used in numerous domains, it has become an increasing interest to not only apply learning techniques for prediction, but to overcome the black box character of many approaches and to explain the underlying reasoning. We will regard several approaches to extract interpretation from machine learning models and to select important variables using statistical approaches. We will contrast approaches with regard to their contributions to interpretability and generalizability.

Learning objectives

• You learn to analyze strengths and weaknesses of explainability and variable selection methods
• You learn to identify open challenges in interpretable learning approaches
• You can present a scientific manuscript in this field and lead a discussion

Requirements

You should have some mathematical background (at least Mathe 1+2 of the ITSE bachelor or comparable) as well as have taken at least one class in machine learning or a related topic. Good Knowledge of English to understand and discuss current literature.

Literature

1. http://statweb.stanford.edu/~tibs/ftp/lars.pdf

2. https://rss.onlinelibrary.wiley.com/doi/full/10.1111/j.1467-9868.2010.00740.x

3. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0130140

4. https://ieeexplore.ieee.org/abstract/document/659721

5. https://arxiv.org/pdf/1606.08813.pdf

Learning

• Seminar for master students 
• Language of instruction: English
• Maximum number of participants: 10

Topics will be presented in the first Session (April 28, 2020). For topic assignments, participants will have to write an E-Mail by May 2^nd, 2020 in which they can give preferences for up to 3 of the presented topics. Then, the topics will be assigned by us. In case of too many applicants, we will decide randomly.

Examination

In the seminar, each participant will give a presentation about a predefined topic within the research area of truth discovery and write a short report. The final grade consists of the following three parts:

• Presentation (45%)
• Written report (35%)
• Discussion in the seminar sessions (20%)

Zurück