Sciweavers

2444 search results - page 75 / 489
» Feature Construction for Back-Propagation
Sort
View
CVPR
2008
IEEE
15 years 12 months ago
Mining compositional features for boosting
The selection of weak classifiers is critical to the success of boosting techniques. Poor weak classifiers do not perform better than random guess, thus cannot help decrease the t...
Junsong Yuan, Jiebo Luo, Ying Wu
ANSOFT
1998
140views more  ANSOFT 1998»
14 years 9 months ago
FORM: A Feature-Oriented Reuse Method with Domain-Specific Reference Architectures
Systematic discovery and exploitation of commonality across related software systems is a fundamental technical requirement for achieving successful software reuse. By examining a...
Kyo Chul Kang, Sajoong Kim, Jaejoon Lee, Kijoo Kim...
SIGCSE
2004
ACM
101views Education» more  SIGCSE 2004»
15 years 3 months ago
Effective features of algorithm visualizations
Many algorithm visualizations have been created, but little is known about which features are most important to their success. We believe that pedagogically useful visualizations ...
Purvi Saraiya, Clifford A. Shaffer, D. Scott McCri...
SMA
1999
ACM
106views Solid Modeling» more  SMA 1999»
15 years 2 months ago
Resolving non-uniqueness in design feature histories
Nearly all major commercial computer-aided design systems have adopted a feature-based design approach to solid modeling. Models are created via a sequence of operations which app...
Vincent A. Cicirello, William C. Regli
ICCV
2011
IEEE
13 years 9 months ago
Latent Low-Rank Representation for Subspace Segmentation and Feature Extraction
Low-Rank Representation (LRR) [16, 17] is an effective method for exploring the multiple subspace structures of data. Usually, the observed data matrix itself is chosen as the dic...
Guangcan Liu, Shuicheng Yan