|
Instructors: Dr. Cornelius Andreas Stefan Weber
Event type:
Lecture
Displayed in timetable as:
DAIS-VL
Hours per week:
4
Language of instruction:
English
Min. | Max. participants:
- | 100
Comments/contents:
We are surrounded by a huge amount of data on a daily basis but only by extracting and analzying information from the data it is possible to discover knowledge. Therefore data-driven intelligent systems have a tremendous implication for many interdisciplinary fields including human computer interaction, assistance systems, cognitive neuroscience and healthcare, and are becoming increasingly relevant for industry. This lecture covers methods, concepts and algorithms of data-driven intelligent systems for knowledge discovery and decision making. The focus is on methods from machine learning, statistics and neural networks, by which a data scientist retrieves interpretable representations from text, speech, images or other data. Topics include:
• Pre-processing and visualization methods
• Knowledge management and associations rules
• Decision trees, decision rules
• Supervised classification and unsupervised clustering
• Neural networks, deep learning and self-organizing neural networks
• Intelligent agents: reinforcement learning and planning
• Ensemble learning and hybrid systems
• Bayes networks and hidden Markov models
• Text mining, sensor mining and other applications
Learning objectives:
The area of Data-driven Intelligent Systems includes concepts of information and knowledge. The students learn on an algorithmic basis how to process and analyse huge amounts of data and how to visualise and interpret data for knowledge discovery and decision making. The students learn how to model complex problems, apply various approaches practically, and work scientifically with systematic methods.
Didactic concept:
Complementary to the lectures is the practical course Data-driven Intelligent Systems, in which lecture topics will be tested and examples will be implemented.
Language:
We will offer the lecture in English to provide an opportunity to become acquainted with the standard language of science and engineering. We will offer the complementing practical courses in English as well as in German to adapt to your preferences. Also we will support you, both for the topic and the language, as good as we can. German discussions are also welcome at any time.
Literature:
- Kantardzic, M. Data Mining. Wiley, 2011.
- Han J. & Kamber, M. Data Mining: Concepts and Techniques. Elsevier/Morgan Kaufmann, Amsterdam, 2006.
- Marsland, S. Machine Learning - An Algorithmic Perspective. CRC Press, 2009.
Additional examination information:
There will be a written examination (Klausur). Dates for the exam will be offered in the beginning and in the end of the non-lecture period.
|
