Sciweavers

2934 search results - page 434 / 587
» Hypothesis Spaces for Learning
Sort
View
ICRA
2002
IEEE
141views Robotics» more  ICRA 2002»
15 years 11 months ago
Movement Imitation with Nonlinear Dynamical Systems in Humanoid Robots
This article presents a new approach to movement planning, on-line trajectory modification, and imitation learning by representing movement plans based on a set of nonlinear diļ¬...
Auke Jan Ijspeert, Jun Nakanishi, Stefan Schaal
CF
2007
ACM
15 years 10 months ago
Fast compiler optimisation evaluation using code-feature based performance prediction
Performance tuning is an important and time consuming task which may have to be repeated for each new application and platform. Although iterative optimisation can automate this p...
Christophe Dubach, John Cavazos, Björn Franke...
UAI
2008
15 years 7 months ago
Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping
We consider the problem of efficiently learning optimal control policies and value functions over large state spaces in an online setting in which estimates must be available afte...
Richard S. Sutton, Csaba Szepesvári, Alborz...
NPL
2006
137views more  NPL 2006»
15 years 6 months ago
Minimal Structure of Self-Organizing HCMAC Neural Network Classifier
The authors previously proposed a self-organizing Hierarchical Cerebellar Model Articulation Controller (HCMAC) neural network containing a hierarchical GCMAC neural network and a ...
Chih-Ming Chen, Yung-Feng Lu, Chin-Ming Hong
TNN
2011
200views more  TNN 2011»
15 years 1 months ago
Domain Adaptation via Transfer Component Analysis
Domain adaptation solves a learning problem in a target domain by utilizing the training data in a different but related source domain. Intuitively, discovering a good feature rep...
Sinno Jialin Pan, Ivor W. Tsang, James T. Kwok, Qi...