3381 search results - page 309 / 677 » LEO - DB2's LEarning Optimizer |
163
click to vote
PKDD
2009
Springer
16 years 19 days ago
2009
Springer
Most existing semi-supervised learning methods are based on the smoothness assumption that data points in the same high density region should have the same label. This assumption, ...
166
Voted
GECCO
2007
Springer
16 years 8 days ago
2007
Springer
We propose a method of knowledge reuse for an ensemble of genetic programming-based learners solving a visual learning task. First, we introduce a visual learning method that uses...
156
click to vote
ICCV
2005
IEEE
15 years 11 months ago
2005
IEEE
This study addresses the problem of unsupervised visual learning. It examines existing popular model order selection criteria before proposes two novel criteria for improving visu...
149
click to vote
GECCO
2005
Springer
15 years 11 months ago
2005
Springer
Code bloat, the excessive increase of code size, is an important issue in Genetic Programming (GP). This paper proposes a theoretical analysis of code bloat in the framework of sy...
142
click to vote
GECCO
2005
Springer
15 years 11 months ago
2005
Springer
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...