Sciweavers

425 search results - page 31 / 85
» Using Stochastic Grammars to Learn Robotic Tasks
Sort
View
IROS
2006
IEEE
107views Robotics» more  IROS 2006»
15 years 7 months ago
Learning Sensory-Motor Maps for Redundant Robots
— Humanoid robots are routinely engaged in tasks requiring the coordination between multiple degrees of freedom and sensory inputs, often achieved through the use of sensorymotor...
Manuel Lopes, José Santos-Victor
GECCO
2003
Springer
268views Optimization» more  GECCO 2003»
15 years 6 months ago
A Generalized Feedforward Neural Network Architecture and Its Training Using Two Stochastic Search Methods
Shunting Inhibitory Artificial Neural Networks (SIANNs) are biologically inspired networks in which the synaptic interactions are mediated via a nonlinear mechanism called shuntin...
Abdesselam Bouzerdoum, Rainer Mueller
ATAL
2009
Springer
15 years 8 months ago
Transfer via soft homomorphisms
The field of transfer learning aims to speed up learning across multiple related tasks by transferring knowledge between source and target tasks. Past work has shown that when th...
Jonathan Sorg, Satinder Singh
ROBOCUP
2004
Springer
111views Robotics» more  ROBOCUP 2004»
15 years 6 months ago
Realtime Object Recognition Using Decision Tree Learning
Abstract. An object recognition process in general is designed as a domain specific, highly specialized task. As the complexity of such a process tends to be rather inestimable, m...
Dirk Wilking, Thomas Röfer
ROBIO
2006
IEEE
129views Robotics» more  ROBIO 2006»
15 years 7 months ago
Learning Utility Surfaces for Movement Selection
— Humanoid robots are highly redundant systems with respect to the tasks they are asked to perform. This redundancy manifests itself in the number of degrees of freedom of the ro...
Matthew Howard, Michael Gienger, Christian Goerick...