Sciweavers

2128 search results - page 375 / 426
» A general characterization of indulgence
Sort
View
FOCS
2008
IEEE
14 years 4 months ago
What Can We Learn Privately?
Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept ...
Shiva Prasad Kasiviswanathan, Homin K. Lee, Kobbi ...
FOCS
2008
IEEE
14 years 4 months ago
Learning Geometric Concepts via Gaussian Surface Area
We study the learnability of sets in Rn under the Gaussian distribution, taking Gaussian surface area as the “complexity measure” of the sets being learned. Let CS denote the ...
Adam R. Klivans, Ryan O'Donnell, Rocco A. Servedio
IJCNN
2008
IEEE
14 years 4 months ago
A comparison of fuzzy ARTMAP and Gaussian ARTMAP neural networks for incremental learning
Abstract— Automatic pattern classifiers that allow for incremental learning can adapt internal class models efficiently in response to new information, without having to retrai...
Eric Granger, Jean-François Connolly, Rober...
INFOCOM
2008
IEEE
14 years 4 months ago
iBubble: Multi-Keyword Routing Protocol for Heterogeneous Wireless Sensor Networks
— Many tasks require multiple sensing capabilities; in Wireless Sensor Networks (WSN), it is expensive to deploy a homogeneous network wherein every sensor has the same functiona...
Xiaoming Lu, Matt Spear, Karl N. Levitt, Shyhtsun ...
IPPS
2008
IEEE
14 years 4 months ago
Random choices for churn resilient load balancing in peer-to-peer networks
Peer-to-peer (P2P) networks based on consistent hashing functions have an inherent load uneven distribution problem. Things are even worse in unstructured P2P systems. The objecti...
Song Fu, Cheng-Zhong Xu, Haiying Shen