Sciweavers

3359 search results - page 101 / 672
» A Simplified Idea Algorithm
Sort
View
TNN
2010
234views Management» more  TNN 2010»
14 years 11 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
ICA
2007
Springer
15 years 11 months ago
Optimization on the Orthogonal Group for Independent Component Analysis
Abstract. This paper derives a new algorithm that performs independent component analysis (ICA) by optimizing the contrast function of the RADICAL algorithm. The core idea of the p...
Michel Journée, Pierre-Antoine Absil, Rodol...
IJCNN
2006
IEEE
15 years 11 months ago
Relative Gradient Learning for Independent Subspace Analysis
Abstract— Independent subspace analysis (ISA) is a generalization of independent component analysis (ICA), where multidimensional ICA is incorporated with the idea of invariant f...
Heeyoul Choi, Seungjin Choi
PVM
2007
Springer
15 years 11 months ago
Full Bandwidth Broadcast, Reduction and Scan with Only Two Trees
We present a new, simple algorithmic idea for exploiting the potential for bidirectional communication present in many modern interconnects for the collective MPI operations broadc...
Peter Sanders, Jochen Speck, Jesper Larsson Tr&aum...
IDEAS
2005
IEEE
72views Database» more  IDEAS 2005»
15 years 10 months ago
Differencing Data Streams
We present external-memory algorithms for differencing large hierarchical datasets. Our methods are especially suited to streaming data with bounded differences. For input sizes m...
Sudarshan S. Chawathe