Teaching
Lecture: Knowledge Representation in Hybrid Architectures /
Wissensrepräsentation in hybriden Architekturen
Summer Semester 2010
News/Aktuelles
Information/Allgemeine Informationen |
| LV-Nummer: |
64-416 |
| Lecturer: |
Prof. Stefan Wermter |
| Period: |
2 UE / Wöchentlich 2 UE Do 12:15-13:45 ab 01.04.10 |
| Room: |
D-129 |
| Credit Hours |
2 SWS |
| Language: |
English |
| Module: |
MV-ISR2-WV2 |
Contents/Inhalte
Our objective is to examine the foundations, representations and applications of
hybrid systems in order to support various themes in intelligent information systems,
cognitive robotics and interactive systems. While traditional approaches have focused
on symbolic representations alone, newer hybrid symbolic/neural/statistical
approaches are often nature-inspired drawing inspirations from biological systems,
neural systems or cognitive performance. We want to explore these foundations in
the context of building more sophisticated adaptive interaction systems, learning
agents, self organising information systems and bio-inspired robotic systems. For
building such nature-inspired computing systems we examine the embedding of
neural, statistical and/or symbolic representations into knowledge-based adaptive
information agents. Applications can include intelligent information systems,
interactive systems, adaptive engineering, data/text mining systems, cognitive and
neuroscience-inspired robots, speech/language systems, intelligent web agents and
hybrid techniques for medical diagnosis. We will teach the concepts linked to and
with examples from our own research projects from the UK and EU.
|
|
Procedure/Vorgehen
The international education gets more and more important for industry, business and
research. In order to help students to prepare for a career in industry or academia
with an international element we suggest that the presentation language will be English. This will be discussed with the students in the first lecture.
Literature/Literatur
Indicative:
- Marsland, S. Machine Learning: An Algorithmic Perspective. 2009.
- Wermter S., Sun R. Hybrid Neural Systems. Springer Verlag, Heidelberg,
2000.
- Wermter S., Riloff E., G. Scheler (Ed). Connectionist, Statistical and
Symbolic Approaches to Learning for Natural Language Processing. Springer Verlag,
Berlin, 1996.
- Haykin S. Neural networks and learning machines. Prentice Hall, 2008
