Sciweavers

44 search results - page 5 / 9
» On updates that constrain the features' connections during l...
Sort
View
ICONIP
1998
13 years 8 months ago
ECOS: Evolving Connectionist Systems and the ECO Learning Paradigm
The paper presents a framework called ECOS for Evolving COnnectionist Systems. ECOS evolve through incremental learning. They can accommodate any new input data, including new fea...
Nikola K. Kasabov
JMLR
2008
169views more  JMLR 2008»
13 years 7 months ago
Multi-class Discriminant Kernel Learning via Convex Programming
Regularized kernel discriminant analysis (RKDA) performs linear discriminant analysis in the feature space via the kernel trick. Its performance depends on the selection of kernel...
Jieping Ye, Shuiwang Ji, Jianhui Chen
ISIM
2007
13 years 9 months ago
Component Model with Support of Mobile Architectures
Common features of current information systems have significant impact on software architectures of these systems. The systems can not be realised as monoliths, formal specifica...
Marek Rychlý
AAAI
2006
13 years 9 months ago
Learning Partially Observable Action Schemas
We present an algorithm that derives actions' effects and preconditions in partially observable, relational domains. Our algorithm has two unique features: an expressive rela...
Dafna Shahaf, Eyal Amir
ICCV
2009
IEEE
13 years 5 months ago
Real-time visual tracking via Incremental Covariance Tensor Learning
Visual tracking is a challenging problem, as an object may change its appearance due to pose variations, illumination changes, and occlusions. Many algorithms have been proposed t...
Yi Wu, Jian Cheng, Jinqiao Wang, Hanqing Lu