Sciweavers

715 search results - page 5 / 143
» Neural Network with Matrix Inputs
Sort
View
TNN
2008
108views more  TNN 2008»
13 years 7 months ago
A Novel Recurrent Neural Network for Solving Nonlinear Optimization Problems With Inequality Constraints
This paper presents a novel recurrent neural network for solving nonlinear optimization problems with inequality constraints. Under the condition that the Hessian matrix of the ass...
Youshen Xia, Gang Feng, Jun Wang
IJCNN
2006
IEEE
14 years 1 months ago
Nonlinear Component Analysis Based on Correntropy
Abstract— In this paper, we propose a new nonlinear principal component analysis based on a generalized correlation function which we call correntropy. The data is nonlinearly tr...
Jian-Wu Xu, Puskal P. Pokharel, António R. ...
ICONIP
2007
13 years 9 months ago
Diverse Evolutionary Neural Networks Based on Information Theory
There is no consensus on measuring distances between two different neural network architectures. Two folds of methods are used for that purpose: Structural and behavioral distance ...
Kyung-Joong Kim, Sung-Bae Cho
ESANN
2006
13 years 8 months ago
Robust Local Cluster Neural Networks
Abstract. Artificial neural networks are intended to be used in future nanoelectronics since their biological examples seem to be robust to noise. In this paper, we analyze the rob...
Ralf Eickhoff, Joaquin Sitte, Ulrich Rückert
ESANN
2004
13 years 8 months ago
Input arrival-time-dependent decoding scheme for a spiking neural network
Spiking neurons model a type of biological neural system where information is encoded with spike times. In this paper, a new method for decoding input spikes according to their abs...
Hesham H. Amin, Robert H. Fujii