Sciweavers

595 search results - page 44 / 119
» Terrain mapping and classification using neural networks
Sort
View
GIS
2004
ACM
16 years 7 months ago
A new approach for a topographic feature-based characterization of digital elevation data
Triangular Irregular Network (TIN) and Regular Square Grid (RSG) are widely used for representing 2.5 dimensional spatial data. However, these models are not defined from the topo...
Eric Saux, Ki-Joune Li, Min-Hwan Kim, Rémy ...
137
Voted
ESANN
2007
15 years 7 months ago
Causality and communities in neural networks
A recently proposed nonlinear extension of Granger causality is used to map the dynamics of a neural population onto a graph, whose community structure characterizes the collective...
Leonardo Angelini, Daniele Marinazzo, Mario Pellic...
134
Voted
PRICAI
2004
Springer
15 years 11 months ago
An Augmentation Hybrid System for Document Classification and Rating
This paper introduces an augmentation hybrid system, referred to as Rated MCRDR. It uses Multiple Classification Ripple Down Rules (MCRDR), a simple and effective knowledge acquisi...
Richard Dazeley, Byeong Ho Kang
161
Voted
ICDAR
2007
IEEE
15 years 10 months ago
WEB Image Classification Based on the Fusion of Image and Text Classifiers
This paper presents a novel method for the classification of images that combines information extracted from the images and contextual information. The main hypothesis is that con...
Pedro R. Kalva, Fabrício Enembreck, Alessan...
ICANN
2010
Springer
15 years 6 months ago
Deep Bottleneck Classifiers in Supervised Dimension Reduction
Deep autoencoder networks have successfully been applied in unsupervised dimension reduction. The autoencoder has a "bottleneck" middle layer of only a few hidden units, ...
Elina Parviainen