Sciweavers

323 search results - page 56 / 65
» Effective Training Methods for Function Localization Neural ...
Sort
View
IJCNN
2008
IEEE
15 years 4 months ago
On the learning of nonlinear visual features from natural images by optimizing response energies
— The operation of V1 simple cells in primates has been traditionally modelled with linear models resembling Gabor filters, whereas the functionality of subsequent visual cortic...
Jussi T. Lindgren, Aapo Hyvärinen
CGO
2010
IEEE
15 years 4 months ago
Automatic creation of tile size selection models
Tiling is a widely used loop transformation for exposing/exploiting parallelism and data locality. Effective use of tiling requires selection and tuning of the tile sizes. This is...
Tomofumi Yuki, Lakshminarayanan Renganarayanan, Sa...
DAS
2008
Springer
14 years 11 months ago
Super-Resolution of Text Images Using Edge-Directed Tangent Field
This paper presents an edge-directed super-resolution algorithm for gray level document images without using any training set. This technique creates an image with smooth regions ...
Jyotirmoy Banerjee, C. V. Jawahar
ICML
2010
IEEE
14 years 10 months ago
Active Learning for Networked Data
We introduce a novel active learning algorithm for classification of network data. In this setting, training instances are connected by a set of links to form a network, the label...
Mustafa Bilgic, Lilyana Mihalkova, Lise Getoor
ACTAC
2006
126views more  ACTAC 2006»
14 years 9 months ago
Named Entity Recognition for Hungarian Using Various Machine Learning Algorithms
In this paper we introduce a statistical Named Entity recognizer (NER) system for the Hungarian language. We examined three methods for identifying and disambiguating proper nouns...
Richárd Farkas, György Szarvas, Andr&a...