Sciweavers

518 search results - page 56 / 104
» Object correspondence as a machine learning problem
Sort
View
AIEDAM
1998
87views more  AIEDAM 1998»
15 years 1 months ago
Learning to set up numerical optimizations of engineering designs
Gradient-based numerical optimization of complex engineering designs offers the promise of rapidly producing better designs. However, such methods generally assume that the object...
Mark Schwabacher, Thomas Ellman, Haym Hirsh
PAMI
2008
302views more  PAMI 2008»
15 years 1 months ago
Learning to Detect Moving Shadows in Dynamic Environments
We propose a novel adaptive technique for detecting moving shadows and distinguishing them from moving objects in video sequences. Most methods for detecting shadows work in a stat...
Ajay J. Joshi, Nikolaos Papanikolopoulos
ECML
2004
Springer
15 years 7 months ago
Batch Reinforcement Learning with State Importance
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....
Lihong Li, Vadim Bulitko, Russell Greiner
CVPR
2010
IEEE
15 years 10 months ago
The Role of Features, Algorithms and Data in Visual Recognition
There are many computer vision algorithms developed for visual (scene and object) recognition. Some systems focus on involved learning algorithms, some leverage millions of trainin...
Devi Parikh and C. Lawrence Zitnick
GECCO
2008
Springer
139views Optimization» more  GECCO 2008»
15 years 3 months ago
Behavior-based speciation for evolutionary robotics
This paper describes a speciation method that allows an evolutionary process to learn several robot behaviors using a single execution. Species are created in behavioral space in ...
Leonardo Trujillo, Gustavo Olague, Evelyne Lutton,...