Sciweavers

772 search results - page 124 / 155
» Shape Regression Machine
Sort
View
CSL
2008
Springer
13 years 7 months ago
A stopping criterion for active learning
Active learning (AL) is a framework that attempts to reduce the cost of annotating training material for statistical learning methods. While a lot of papers have been presented on...
Andreas Vlachos
DATAMINE
2006
157views more  DATAMINE 2006»
13 years 7 months ago
Data Clustering with Partial Supervision
Clustering with partial supervision finds its application in situations where data is neither entirely nor accurately labeled. This paper discusses a semisupervised clustering algo...
Abdelhamid Bouchachia, Witold Pedrycz
JMLR
2006
156views more  JMLR 2006»
13 years 7 months ago
Large Scale Multiple Kernel Learning
While classical kernel-based learning algorithms are based on a single kernel, in practice it is often desirable to use multiple kernels. Lanckriet et al. (2004) considered conic ...
Sören Sonnenburg, Gunnar Rätsch, Christi...
NECO
2007
115views more  NECO 2007»
13 years 7 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...
ISNN
2010
Springer
13 years 6 months ago
MULP: A Multi-Layer Perceptron Application to Long-Term, Out-of-Sample Time Series Prediction
Abstract. A forecasting approach based on Multi-Layer Perceptron (MLP) Artificial Neural Networks (named by the authors MULP) is proposed for the NN5 111 time series long-term, out...
Eros Pasero, Giovanni Raimondo, Suela Ruffa