Sciweavers

179 search results - page 5 / 36
» Neural Learning from Unbalanced Data Using Noise Modeling
Sort
View
GIS
2008
ACM
14 years 9 months ago
Fast and extensible building modeling from airborne LiDAR data
This paper presents an automatic algorithm which reconstructs building models from airborne LiDAR (light detection and ranging) data of urban areas. While our algorithm inherits t...
Qian-Yi Zhou, Ulrich Neumann
WSOM
2009
Springer
14 years 3 months ago
Approaching the Time Dependent Cocktail Party Problem with Online Sparse Coding Neural Gas
Abstract. We show how the “Online Sparse Coding Neural Gas” algorithm can be applied to a more realistic model of the “Cocktail Party Problem”. We consider a setting where ...
Kai Labusch, Erhardt Barth, Thomas Martinetz
IAJIT
2010
102views more  IAJIT 2010»
13 years 7 months ago
Multilayer neural network-burg combination for acoustical detection of buried objects
: A Burg technique is employed to model the long wavelength localization and imaging problem. A Burg method is used as a high resolution and stable technique. The idea of in-line h...
Mujahid Al-Azzo, Lubna Badri
SIGIR
2008
ACM
13 years 8 months ago
Learning to reduce the semantic gap in web image retrieval and annotation
We study in this paper the problem of bridging the semantic gap between low-level image features and high-level semantic concepts, which is the key hindrance in content-based imag...
Changhu Wang, Lei Zhang 0001, Hong-Jiang Zhang
COLT
1995
Springer
14 years 10 days ago
Regression NSS: An Alternative to Cross Validation
The Noise Sensitivity Signature (NSS), originally introduced by Grossman and Lapedes (1993), was proposed as an alternative to cross validation for selecting network complexity. I...
Michael P. Perrone, Brian S. Blais