202 search results - page 9 / 41 » How Local Should a Learning Method Be |
99
Voted
CEC
2005
IEEE
15 years 8 months ago
2005
IEEE
AbstractThis paper presents a real-coded memetic algorithm that combines a high diversity global exploration with an adaptive local search method to the most promising individuals ...
123
Voted
NIPS
2004
15 years 3 months ago
2004
Many machine learning algorithms for clustering or dimensionality reduction take as input a cloud of points in Euclidean space, and construct a graph with the input data points as...
140
click to vote
PUK
2000
15 years 3 months ago
2000
Abstract. In the stream of research that aims to speed up practical planners, we propose a new approach to task planning based on Probabilistic Roadmap Methods (PRM). Our contribut...
105
Voted
ICCAD
1997
IEEE
15 years 6 months ago
1997
IEEE
An algorithm that remains in use at the core of many partitioning systems is the Kernighan-Lin algorithm and a variant the Fidducia-Matheysses (FM) algorithm. To understand the FM...
136
Voted
CVPR
2010
IEEE
2010
IEEE
Learning a Hierarchy of Discriminative Space-Time Neighborhood Features for Human Action Recognition
15 years 10 months ago
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...