Sciweavers

2924 search results - page 412 / 585
» On the Use of Evidence in Neural Networks
Sort
View
MSWIM
2005
ACM
15 years 7 months ago
YAES: a modular simulator for mobile networks
Developing network protocols for mobile wireless systems is a complex task, and most of the existing simulator frameworks are not well suited for experimental development. The YAE...
Ladislau Bölöni, Damla Turgut
ENGL
2007
71views more  ENGL 2007»
15 years 1 months ago
Inductive Classifying Artificial Network for Fly Ash Type Categorization
Nowadays, fly ash is a common ingredient of concrete and may constitute up to 50% by weight of the total binder material. Incorporation of fly ash in Portland-cement concrete is hi...
M. C. Nataraja, M. A. Jayaram, C. N. Ravikumar
NECO
2007
115views more  NECO 2007»
15 years 1 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
IJCNN
2008
IEEE
15 years 8 months ago
Fully complex-valued radial basis function networks for orthogonal least squares regression
— We consider a fully complex-valued radial basis function (RBF) network for regression application. The locally regularised orthogonal least squares (LROLS) algorithm with the D...
Sheng Chen, Xia Hong, Chris J. Harris
WWW
2010
ACM
15 years 9 months ago
Predicting positive and negative links in online social networks
We study online social networks in which relationships can be either positive (indicating relations such as friendship) or negative (indicating relations such as opposition or ant...
Jure Leskovec, Daniel P. Huttenlocher, Jon M. Klei...