Sciweavers

374 search results - page 61 / 75
» Training the random neural network using quasi-Newton method...
Sort
View
ICANN
2009
Springer
15 years 6 months ago
Basis Decomposition of Motion Trajectories Using Spatio-temporal NMF
Abstract. This paper’s intention is to present a new approach for decomposing motion trajectories. The proposed algorithm is based on nonnegative matrix factorization, which is a...
Sven Hellbach, Julian Eggert, Edgar Körner, H...
ACTAC
2006
126views more  ACTAC 2006»
14 years 11 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...
ICIP
2003
IEEE
16 years 1 months ago
Compressed domain human motion recognition using motion history information
In this paper we present a system for classifying various human actions in compressed domain video framework. We introduce the notion of quantifying the motion involved, through w...
R. Venkatesh Babu, K. R. Ramakrishnan
IROS
2008
IEEE
141views Robotics» more  IROS 2008»
15 years 6 months ago
Active sensing based dynamical object feature extraction
— This paper presents a method to autonomously extract object features that describe their dynamics from active sensing experiences. The model is composed of a dynamics learning ...
Shun Nishide, Tetsuya Ogata, Ryunosuke Yokoya, Jun...
IJCNN
2008
IEEE
15 years 6 months ago
Learning adaptive subject-independent P300 models for EEG-based brain-computer interfaces
Abstract— This paper proposes an approach to learn subjectindependent P300 models for EEG-based brain-computer interfaces. The P300 models are first learned using a pool of exis...
Shijian Lu, Cuntai Guan, Haihong Zhang