Sciweavers

1136 search results - page 145 / 228
» Learning with Weighted Transducers
Sort
View
CONNECTION
2004
92views more  CONNECTION 2004»
13 years 9 months ago
High capacity associative memories and connection constraints
: High capacity associative neural networks can be built from networks of perceptrons, trained using simple perceptron training. Such networks perform much better than those traine...
Neil Davey, Rod Adams
IJON
2002
103views more  IJON 2002»
13 years 8 months ago
RBF networks training using a dual extended Kalman filter
: A new supervised learning procedure for training RBF networks is proposed. It uses a pair of parallel running Kalman filters to sequentially update both the output weights and th...
Iulian B. Ciocoiu
INFOCOM
2010
IEEE
13 years 7 months ago
Throughput-Optimal Opportunistic Scheduling in the Presence of Flow-Level Dynamics
Abstract—We consider multiuser scheduling in wireless networks with channel variations and flow-level dynamics. Recently, it has been shown that the MaxWeight algorithm, which i...
Shihuan Liu, Lei Ying, R. Srikant
ICWSM
2009
13 years 6 months ago
Delta TFIDF: An Improved Feature Space for Sentiment Analysis
Mining opinions and sentiment from social networking sites is a popular application for social media systems. Common approaches use a machine learning system with a bag of words f...
Justin Martineau, Tim Finin
JDCTA
2010
163views more  JDCTA 2010»
13 years 4 months ago
An Approach to Traffic Volume Forecasting Based on Ant Colony Neural Network
Combining the ant colony algorithm (ACA) and the neural network (NN), the present paper puts forward an approach to traffic volume forecasting based on the ant colony neural netwo...
Hong Chen