Sciweavers

ESANN
2001
14 years 28 days ago
Transfer functions: hidden possibilities for better neural networks
Abstract. Sigmoidal or radial transfer functions do not guarantee the best generalization nor fast learning of neural networks. Families of parameterized transfer functions provide...
Wlodzislaw Duch, Norbert Jankowski
ESANN
2001
14 years 28 days ago
Penalized least squares, model selection, convex hull classes and neural nets
We develop improved risk bounds for function estimation with models such as single hidden layer neural nets, using a penalized least squares criterion to select the size of the mod...
Gerald H. L. Cheang, Andrew R. Barron
ESANN
2001
14 years 28 days ago
Applications of neuro-fuzzy classification, evaluation and forecasting techniques in agriculture
Aim of the present article is to show the results obtained from the application of neuro-fuzzy methodology in the solution of agriculture problems like the Bactrocera Oleae (olive...
Elena Bellei, Diego Guidotti, Ruggero Petacchi, Le...
ESANN
2001
14 years 28 days ago
Canonical correlation analysis in early vision processing
This paper illustrates how canonical correlation analysis can be used for designing efficient visual operators by learning. The approach is highly task oriented and what constitute...
Magnus Borga, Hans Knutsson
ESANN
2001
14 years 28 days ago
Intelligent hardware for identification and control of non-linear systems with SVM
Support Vector Machines are gaining more and more acceptance thanks to their success in many real
Andrea Boni, Fabio Bardi
ESANN
2001
14 years 28 days ago
Some known facts about financial data
: Many researchers are interesting in applying the neural networks methods to financial data. In fact these data are very complex, and classical methods do not always give satisfac...
Eric de Bodt, Joseph Rynkiewicz, Marie Cottrell
ESANN
2006
14 years 28 days ago
Weighted differential topographic function: a refinement of topographic function
Topology preservation of Self-Organizing Maps (SOMs) is an advantageous property for correct clustering. Among several existing measures of topology violation, this paper studies t...
Lili Zhang, Erzsébet Merényi
ESANN
2006
14 years 28 days ago
Optimal design of hierarchical wavelet networks for time-series forecasting
The purpose of this study is to identify the Hierarchical Wavelet Neural Networks (HWNN) and select important input features for each sub-wavelet neural network automatically. Base...
Yuehui Chen, Bo Yang, Ajith Abraham
ESANN
2006
14 years 28 days ago
Visualizing gene interaction graphs with local multidimensional scaling
Several bioinformatics data sets are naturally represented as graphs, for instance gene regulation, metabolic pathways, and proteinprotein interactions. The graphs are often large ...
Jarkko Venna, Samuel Kaski