Sciweavers

2033 search results - page 351 / 407
» Semi-Supervised Support Vector Machines
Sort
View
NECO
2007
115views more  NECO 2007»
13 years 8 months ago
Training Recurrent Networks by Evolino
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
Jürgen Schmidhuber, Daan Wierstra, Matteo Gag...
PR
2007
133views more  PR 2007»
13 years 8 months ago
Incorporating multiple SVMs for automatic image annotation
In this paper, a novel automatic image annotation system is proposed, which integrates two sets of support vector machines (SVMs), namely the multiple instance learning (MIL)-base...
Xiaojun Qi, Yutao Han
SAC
2008
ACM
13 years 8 months ago
Author identification using writer-dependent and writer-independent strategies
In this work we discuss author identification for documents written in Portuguese. Two different approaches were compared. The first is the writer-independent model which reduces ...
Daniel Pavelec, Edson J. R. Justino, Leonardo Vida...
ICPR
2010
IEEE
13 years 8 months ago
Robust ECG Biometrics by Fusing Temporal and Cepstral Information
—The use of vital signs as a biometric is a potentially viable approach in a variety of application scenarios such as security and personalized health care. In this paper, a nove...
Ming Li, Shrikanth Narayanan
ICRA
2010
IEEE
164views Robotics» more  ICRA 2010»
13 years 7 months ago
Boundary detection based on supervised learning
— Detecting the boundaries of objects is a key step in separating foreground objects from the background, which is useful for robotics and computer vision applications, such as o...
Kiho Kwak, Daniel F. Huber, Jeongsook Chae, Takeo ...