Teaching
Integrated Seminar: Knowledge Representation in Hybrid Architectures /Wissensrepräsentation in hybriden Architekturen
Summer Semester 2010
Information/Allgemeine Informationen |
| LV-Nummer: |
64-417 |
| Lecturer: |
Prof. Stefan Wermter |
| Period: |
2 UE / Wöchentlich 2 UE Fr 12:15-13:45 ab 09.04.10 |
| Room: |
D-129 |
| Credit Hours |
2 SWS |
| Language: |
English/Deutsch |
| Module: |
MV-ISR2-WV2 |
Contents/Inhalte
We plan to cover the topics including
- Neuroscience-inspired Architectures
- Spiking
neural networks -Midbrain / Cortical Architectures
- Mirror Neuron Theory
- Neuroscience-inspired Robotics
- Bayesian Belief Networks
- Hybrid representations in
natural language processing
- Hybrid representations in robotics
- Multimodal integration
- Integration of symbolic, neural and statistical approaches
Objective/Lernziel
Critically analyse and evaluate scientific literature and research in the area of
integration of neural and symbolic representations.
Procedure/Vorgehen
This seminar will be run in the style of a "journal club" or "brown bag seminar
series". Presentations or demos will be given by the students, followed by discussion
and written analysis papers. 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 seminar.
Literature/Literatur
- Wermter S., M. Page, M. Knowles, V. Gallese, F. Pulvermüller and J. Taylor. Neural Network: Special Issue on What it Means to Communicate. Volume 22,
Number 2, March, 2009.
- Wermter S., Palm G., Elshaw M. (Eds.). Biomimetic Neural Learning for Intelligent Robots. Springer, Heidelberg, Germany, 2005.
- Wermter S., Austin J., Willshaw D. (Eds.). Emergent Neural Computational Architectures based on Neuroscience. Springer, Heidelberg, Germany, 2001.
Material
