Self-organizing neural architectures are described for the visual perception of static and moving forms, for autonomous real-time learning of multidimensional associative maps, and for adaptive control of variable-speed multi joint motor trajectories. Motion filtering and segmentation are carried out by a motion Boundary Contour System. Associative learning is accomplished by a Vector Associative Map, which provides an on-line alternative to the off-line properties of Back Propagation for error-based learning. Trajectory formation is carried out by a Vector Integration to Endpoint model.
Self-Organizing Neural Architectures for Vision, Learning, and Robotic Control
International Neural Network Conference ; Kapitel : 92 ; 797-800
1990-01-01
4 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Self-Organizing Ad-hoc Mobile Robotic Networks
TIBKAT | 2012
|Existing Robotic Control Architectures
Springer Verlag | 2015
|Vibration control of building structures using self-organizing and self-learning neural networks
Online Contents | 2005
|Self-organizing Control Techniques for Modular Robotic Arms within Space Applications
British Library Conference Proceedings | 2005
|View-based route-learning with self-organizing neural networks
British Library Online Contents | 2001
|