[2022] Interactive Machine Learning: Visualization & Explainability
This course gives an introduction to the design of mixed-initiative systems.
Announcements
- Tutorials will start in the first week of the semester (Thu 17-18 CAB G 11).
- The framework for the practical projects will be demonstrated in the second and third tutorials.
- All materials and links can be accessed using your NETHZ credentials.
- The lectures are offered in presence and via Zoom. We encourage all students to attend the in-person lecture if possible.
- During lectures, we will offer a chat for asking questions. The chat is moderated by a teaching assistant (TA). Please do not ask questions via Zoom.
Introduction
Interactive, mixed-initiative machine learning promises to combine the efficiency of automation with the effectiveness of humans for a collaborative decision-making and problem-solving process. This can be facilitated through co-adaptive visual interfaces.
This course will first introduce the foundations of information visualization design based on data charecteristics, e.g., high-dimensional, geo-spatial, relational, temporal, and textual data.
Second, we will discuss interaction techniques and explanation strategies to enable explainable machine learning with the tasks of understanding, diagnosing, and refining machine learning models.
Learning Objectives
The goal of the course is to introduce techniques for interactive information visualization and to apply these on understanding, diagnosing, and refining machine learning models.
Schedule
The course is structured into five blocks covering the following topics:
- Foundations
- Visualization
- Interaction
- Explainability
- Outlook
Course Materials
Course materials will be made available on the Moodle platform.
For an overview of the student project results; external pageclick here.
Questions
To allow for an optimal flow of information, please ask your content-related questions on Moodle rather than via email. In this manner, your question and our answer are visible to everyone. Consequently, please read existing question-answer pairs before asking new questions.