Sciweavers

2924 search results - page 526 / 585
» On the Use of Evidence in Neural Networks
Sort
View
ICANN
2009
Springer
15 years 8 months ago
Learning Features by Contrasting Natural Images with Noise
Abstract. Modeling the statistical structure of natural images is interesting for reasons related to neuroscience as well as engineering. Currently, this modeling relies heavily on...
Michael Gutmann, Aapo Hyvärinen
BIBM
2008
IEEE
172views Bioinformatics» more  BIBM 2008»
15 years 8 months ago
Boosting Methods for Protein Fold Recognition: An Empirical Comparison
Protein fold recognition is the prediction of protein’s tertiary structure (Fold) given the protein’s sequence without relying on sequence similarity. Using machine learning t...
Yazhene Krishnaraj, Chandan K. Reddy
CEC
2008
IEEE
15 years 8 months ago
Automatic model type selection with heterogeneous evolution: An application to RF circuit block modeling
— Many complex, real world phenomena are difficult to study directly using controlled experiments. Instead, the use of computer simulations has become commonplace as a cost effe...
Dirk Gorissen, Luciano De Tommasi, Jeroen Croon, T...
IJCNN
2007
IEEE
15 years 8 months ago
Branching Principal Components: Elastic Graphs, Topological Grammars and Metro Maps
— To approximate complex data, we propose new type of low-dimensional “principal object”: principal cubic complex. This complex is a generalization of linear and nonlinear pr...
Alexander N. Gorban, Neil R. Sumner, Andrei Yu. Zi...
IJCNN
2007
IEEE
15 years 8 months ago
Predictive E-Mail Server Performability Analysis Based on Fuzzy Arithmetic
–The performability of disk arrays systems has been studied before. However, in the case of imprecise data, a fuzzy model can be the base for the performability analysis. This pa...
Guillermo Navarro, Milos Manic