Sciweavers

3076 search results - page 274 / 616
» Active Learning for Networked Data
Sort
View
TCS
2008
15 years 6 months ago
Security types for dynamic web data
We describe a type system for the Xd calculus of Gardner and Maffeis. An Xd-network is a network of locations, where each location consists of both a data tree (which contains scr...
Mariangiola Dezani-Ciancaglini, Silvia Ghilezan, J...
IJCNN
2007
IEEE
16 years 14 days ago
Parallel Learning of Large Fuzzy Cognitive Maps
— Fuzzy Cognitive Maps (FCMs) are a class of discrete-time Artificial Neural Networks that are used to model dynamic systems. A recently introduced supervised learning method, wh...
Wojciech Stach, Lukasz A. Kurgan, Witold Pedrycz
ICDCSW
2008
IEEE
16 years 19 days ago
Real-Time Data Services for Cyber Physical Systems
Cyber Physical Systems (CPSs) have grand visions with great socio-economic impacts such as blackout-free electricity supply and real-time disaster recovery. A key challenge is pro...
Kyoung-Don Kang, Sang Hyuk Son
NECO
2008
146views more  NECO 2008»
15 years 6 months ago
Deep, Narrow Sigmoid Belief Networks Are Universal Approximators
In this paper we show that exponentially deep belief networks [3, 7, 4] can approximate any distribution over binary vectors to arbitrary accuracy, even when the width of each lay...
Ilya Sutskever, Geoffrey E. Hinton
ANNS
2007
15 years 7 months ago
An improved architecture for cooperative and comparative neurons (CCNs) in neural network
The ability to store and retrieve information is critical in any type of neural network. In neural network, the memory particularly associative memory, can be defined as the one i...
Md. Kamrul Islam