Sciweavers

192 search results - page 33 / 39
» A Note on the Decomposition Methods for Support Vector Regre...
Sort
View
NECO
2007
115views more  NECO 2007»
13 years 8 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...
KDD
2003
ACM
142views Data Mining» more  KDD 2003»
14 years 9 months ago
Frequent-subsequence-based prediction of outer membrane proteins
A number of medically important disease-causing bacteria (collectively called Gram-negative bacteria) are noted for the extra "outer" membrane that surrounds their cell....
Rong She, Fei Chen 0002, Ke Wang, Martin Ester, Je...
SIGIR
2004
ACM
14 years 2 months ago
On scaling latent semantic indexing for large peer-to-peer systems
The exponential growth of data demands scalable infrastructures capable of indexing and searching rich content such as text, music, and images. A promising direction is to combine...
Chunqiang Tang, Sandhya Dwarkadas, Zhichen Xu
BMCBI
2008
140views more  BMCBI 2008»
13 years 8 months ago
SCPRED: Accurate prediction of protein structural class for sequences of twilight-zone similarity with predicting sequences
Background: Protein structure prediction methods provide accurate results when a homologous protein is predicted, while poorer predictions are obtained in the absence of homologou...
Lukasz A. Kurgan, Krzysztof J. Cios, Ke Chen 0003
BMCBI
2008
158views more  BMCBI 2008»
13 years 8 months ago
Real value prediction of protein solvent accessibility using enhanced PSSM features
Background: Prediction of protein solvent accessibility, also called accessible surface area (ASA) prediction, is an important step for tertiary structure prediction directly from...
Darby Tien-Hao Chang, Hsuan-Yu Huang, Yu-Tang Syu,...