Zobrazeno 1 - 10
of 100
pro vyhledávání: '"Der, Ralf"'
Publikováno v:
Report / Institut für Informatik.
We study the extraction of nonlinear data models in high-dimensional spaces with modified self-organizing maps. We present a general algorithm which maps low-dimensional lattices into high-dimensional data manifolds without violation of topology. The
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A34520
https://ul.qucosa.de/api/qucosa%3A34520/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A34520/attachment/ATT-0/
Publikováno v:
Report / Institut für Informatik.
Measurement noise reduction and parameter estimation is a topic of central importance in plant control. The complexity of real world plants and the working conditions in practice require robust real-time algorithms which are easy to implement, simple
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A34519
https://ul.qucosa.de/api/qucosa%3A34519/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A34519/attachment/ATT-0/
Publikováno v:
Report / Institut für Informatik.
Generalized principal curves are capable of representing complex data structures as they may have branching points or may consist of disconnected parts. For their construction using an unsupervised learning algorithm the templates need to be structur
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A34516
https://ul.qucosa.de/api/qucosa%3A34516/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A34516/attachment/ATT-0/
Autor:
Der, Ralf, Steinmetz, Ulrich
Publikováno v:
Report / Institut für Informatik.
Cognitive processes heavily rely on a dedicated spatio-temporal architecture of the underlying neural system - the brain. The spatial aspect is substantiated by the modularization as it has been brought to light in much detail by recent sophisticated
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A34518
https://ul.qucosa.de/api/qucosa%3A34518/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A34518/attachment/ATT-0/
Autor:
Der, Ralf, Herrmann, Michael
We present a variant of the Q-learning algorithm with automatic control of the exploration rate by a competition scheme. The theoretical approach is accompanied by systematic simulations of a chaos control task. Finally, we give interpretations of th
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A32411
https://ul.qucosa.de/api/qucosa%3A32411/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A32411/attachment/ATT-0/
We study the extraction of nonlinear data models in high dimensional spaces with modified self-organizing maps. Our algorithm maps lower dimensional lattice into a high dimensional space without topology violations by tuning the neighborhood widths l
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A32410
https://ul.qucosa.de/api/qucosa%3A32410/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A32410/attachment/ATT-0/
Autor:
Herrmann, Michael, Der, Ralf
Q-learning as well as other learning paradigms depend strongly on the representation of the underlying state space. As a special case of the hidden state problem we investigate the effect of a self-organizing discretization of the state space in a si
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A32942
https://ul.qucosa.de/api/qucosa%3A32942/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A32942/attachment/ATT-0/
Autor:
Der, Ralf, Smyth, Darragh
One of the goals of perception is to learn to respond to coherence across space, time and modality. Here we present an abstract framework for the local online unsupervised learning of this coherent information using multi-stream neural networks. The
Externí odkaz:
https://ul.qucosa.de/id/qucosa%3A32448
https://ul.qucosa.de/api/qucosa%3A32448/attachment/ATT-0/
https://ul.qucosa.de/api/qucosa%3A32448/attachment/ATT-0/
Autor:
Der, Ralf, Martius, Georg
With the accelerated development of robot technologies, optimal control becomes one of the central themes of research. In traditional approaches, the controller, by its internal functionality, finds appropriate actions on the basis of the history of
Externí odkaz:
http://arxiv.org/abs/1602.02990