Sciweavers

658 search results - page 113 / 132
» Solution of the Train Platforming Problem
Sort
View
NECO
1998
83views more  NECO 1998»
13 years 8 months ago
Properties of Support Vector Machines
Support Vector Machines (SVMs) perform pattern recognition between two point classes by nding a decision surface determined by certain points of the training set, termed Support V...
Massimiliano Pontil, Alessandro Verri
TNN
1998
111views more  TNN 1998»
13 years 8 months ago
Modular recurrent neural networks for Mandarin syllable recognition
Abstract—A new modular recurrent neural network (MRNN)based speech-recognition method that can recognize the entire vocabulary of 1280 highly confusable Mandarin syllables is pro...
Sin-Horng Chen, Yuan-Fu Liao
MICCAI
2010
Springer
13 years 7 months ago
3D Knowledge-Based Segmentation Using Pose-Invariant Higher-Order Graphs
Segmentation is a fundamental problem in medical image analysis. The use of prior knowledge is often considered to address the ill-posedness of the process. Such a process consists...
Chaohui Wang, Olivier Teboul, Fabrice Michel, Salm...
TIP
2010
154views more  TIP 2010»
13 years 7 months ago
Projective Nonnegative Graph Embedding
—We present in this paper a general formulation for nonnegative data factorization, called projective nonnegative graph embedding (PNGE), which 1) explicitly decomposes the data ...
Xiaobai Liu, Shuicheng Yan, Hai Jin
NAACL
2010
13 years 6 months ago
Minimally-Supervised Extraction of Entities from Text Advertisements
Extraction of entities from ad creatives is an important problem that can benefit many computational advertising tasks. Supervised and semi-supervised solutions rely on labeled da...
Sameer Singh, Dustin Hillard, Chris Leggetter