Sciweavers

715 search results - page 68 / 143
» Neural Network with Matrix Inputs
Sort
View
ICANN
2007
Springer
14 years 2 months ago
Recursive Principal Component Analysis of Graphs
Treatment of general structured information by neural networks is an emerging research topic. Here we show how representations for graphs preserving all the information can be devi...
Alessio Micheli, Alessandro Sperduti
ICANN
1997
Springer
14 years 27 days ago
Kernel Principal Component Analysis
A new method for performing a nonlinear form of Principal Component Analysis is proposed. By the use of integral operator kernel functions, one can e ciently compute principal comp...
Bernhard Schölkopf, Alex J. Smola, Klaus-Robe...
CBMS
2007
IEEE
13 years 9 months ago
A Time-Frequency Based Method for the Detection of Epileptic Seizures in EEG Recordings
A novel three-stage method for the analysis of electroencephalographic (EEG) signals, concerning epileptic seizures, is proposed. First, segments of the EEG signals are analyzed u...
Alexandros T. Tzallas, Markos G. Tsipouras, Dimitr...
NC
2011
236views Neural Networks» more  NC 2011»
12 years 11 months ago
Graph multiset transformation: a new framework for massively parallel computation inspired by DNA computing
In this paper, graph multiset transformation is introduced and studied as a novel type of parallel graph transformation. The basic idea is that graph transformation rules may be ap...
Hans-Jörg Kreowski, Sabine Kuske
ICANN
2005
Springer
14 years 2 months ago
Accurate and Robust Image Superresolution by Neural Processing of Local Image Representations
Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require ite...
Carlos Miravet, Francisco de Borja Rodrígue...