Disputation von Junpei Zhong am 17.4.2015, 10:15 Uhr, D-220

17. April 2015, von Reinhard Zierke

Einladung zur hochschulöffentlichen Disputation

von Herrn Junpei Zhong:

“Artificial Neural Models for Feedback Pathways for Sen- sorimotor Integration”

Einladung zur hochschulöffentlichen Disputation

von Herrn Junpei Zhong

Freitag, 17. April 2015 10:15 Uhr
im Informatikum, Vogt-Kölln-Straße 30, Raum D-220

“Artificial Neural Models for Feedback Pathways for Sen- sorimotor Integration”

Abstract:

The brain comprises hierarchical modules on various physiological levels. Neural feedback signals modulate the neural activities via inhibitory or excitatory connections within/between these levels. They have predictive and filtering functions on the neuronal population coding of the bottom-up sensory-driven signals in the perception-action system. In this thesis, we propose that the pre-dictive role of the feedback pathways at most levels of action and perception can be modelled by the recurrent connections in different artificial cognitive platforms. This will be examined by three recurrent neural network models. Furthermore, the three models and experiments with them show that the recurrent neural networks are able to model feedback pathways and to exhibit the feedback-related sensorimotor predictive functions.

Betreuer: Prof. Dr. Stefan Wermter

Prof. Dr. Matthias Rarey
(Vorsitzender des Fach-Promotionsausschusses Informatik)