Sciweavers

130 search results - page 7 / 26
» Meaning Representation: From Continuity to Discreteness
Sort
View
MICAI
2009
Springer
14 years 4 months ago
A Two-Stage Relational Reinforcement Learning with Continuous Actions for Real Service Robots
Reinforcement Learning is a commonly used technique in robotics, however, traditional algorithms are unable to handle large amounts of data coming from the robot’s sensors, requi...
Julio H. Zaragoza, Eduardo F. Morales
MM
2005
ACM
154views Multimedia» more  MM 2005»
14 years 3 months ago
Determining structure in continuously recorded videos
In this paper, we present a scene detection framework on continuously recorded videos. Conventional temporal scene segmentation methods work for the videos composed of discrete sh...
Yun Zhai, Mubarak Shah
VISSYM
2003
13 years 11 months ago
Hierarchical Isosurface Segmentation Based on Discrete Curvature
A high-level approach to describe the characteristics of a surface is to segment it into regions of uniform curehavior and construct an abstract representation given by a (topolog...
Fabien Vivodtzev, Lars Linsen, Georges-Pierre Bonn...
GECCO
2006
Springer
156views Optimization» more  GECCO 2006»
14 years 1 months ago
Probabilistic modeling for continuous EDA with Boltzmann selection and Kullback-Leibeler divergence
This paper extends the Boltzmann Selection, a method in EDA with theoretical importance, from discrete domain to the continuous one. The difficulty of estimating the exact Boltzma...
Yunpeng Cai, Xiaomin Sun, Peifa Jia
EUSFLAT
2009
103views Fuzzy Logic» more  EUSFLAT 2009»
13 years 7 months ago
Possibility Distribution: a unified representation for parameter estimation
Abstract-- the paper presents a possibility formulation of oneparameter estimation that unifies some usual probability formulations. Point and confidence interval estimation are un...
Gilles Mauris