Sciweavers

261 search results - page 49 / 53
» Active Learning for Robot Manipulation
Sort
View
ECCV
1994
Springer
13 years 11 months ago
Integration and Control of Reactive Visual Processes
This paper describes a new approach to the integration and control of continuously operating visual processes. Visual processes are expressed as transformations which map signals ...
James L. Crowley, Jean Marc Bedrune, Morten Bekker...
CEC
2009
IEEE
13 years 11 months ago
Automatic system identification based on coevolution of models and tests
In evolutionary robotics, controllers are often designed in simulation, then transferred onto the real system. Nevertheless, when no accurate model is available, controller transfe...
Sylvain Koos, Jean-Baptiste Mouret, Stéphan...
ICANN
2003
Springer
14 years 26 days ago
The Acquisition of New Categories through Grounded Symbols: An Extended Connectionist Model
Abstract. Solutions to the symbol grounding problem, in psychologically plausible cognitive models, have been based on hybrid connectionist/symbolic architectures, on robotic appro...
Alberto Greco, Thomas Riga, Angelo Cangelosi
BC
2002
193views more  BC 2002»
13 years 7 months ago
Resonant spatiotemporal learning in large random recurrent networks
Taking a global analogy with the structure of perceptual biological systems, we present a system composed of two layers of real-valued sigmoidal neurons. The primary layer receives...
Emmanuel Daucé, Mathias Quoy, Bernard Doyon
DAGSTUHL
2003
13 years 9 months ago
Removing Some 'A' from AI: Embodied Cultured Networks
We embodied networks of cultured biological neurons in simulation and in robotics. This is a new research paradigm to study learning, memory, and information processing in real tim...
Douglas J. Bakkum, Alexander C. Shkolnik, Guy Ben-...