Sciweavers

1215 search results - page 189 / 243
» Dimensions of machine learning in design
Sort
View
IJCNN
2008
IEEE
14 years 4 months ago
Evolving a neural network using dyadic connections
—Since machine learning has become a tool to make more efficient design of sophisticated systems, we present in this paper a novel methodology to create powerful neural network ...
Andreas Huemer, Mario A. Góngora, David A. ...
CIVR
2007
Springer
231views Image Analysis» more  CIVR 2007»
14 years 4 months ago
Classification of video events using 4-dimensional time-compressed motion features
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
Alexander Haubold, Milind R. Naphade
ECCV
2008
Springer
15 years 20 hour ago
Viewpoint Invariant Pedestrian Recognition with an Ensemble of Localized Features
Viewpoint invariant pedestrian recognition is an important yet under-addressed problem in computer vision. This is likely due to the difficulty in matching two objects with unknown...
Douglas Gray, Hai Tao
ECTEL
2007
Springer
14 years 4 months ago
Role Based Access Control for the Interaction with Search Engines
Search engine-based features are a basic interaction mean for users to find information inside a Web-based Learning Management Systems (LMS); nonetheless, traditional solutions la...
Alessandro Bozzon, Tereza Iofciu, Wolfgang Nejdl, ...
AAAI
2008
14 years 14 days ago
Constrained Classification on Structured Data
Most standard learning algorithms, such as Logistic Regression (LR) and the Support Vector Machine (SVM), are designed to deal with i.i.d. (independent and identically distributed...
Chi-Hoon Lee, Matthew R. G. Brown, Russell Greiner...