Sciweavers

Share
AINA
2010
IEEE
8 years 8 months ago
Neural Network Trainer through Computer Networks
- This paper introduces a neural network training tool through computer networks. The following algorithms, such as neuron by neuron (NBN) [1][2], error back propagation (EBP), Lev...
Nam Pham, Hao Yu, Bogdan M. Wilamowski
IJDLS
2010
108views more  IJDLS 2010»
8 years 9 months ago
Sampling the Web as Training Data for Text Classification
Data acquisition is a major concern in text classification. The excessive human efforts required by conventional methods to build up quality training collection might not always b...
Wei-Yen Day, Chun-Yi Chi, Ruey-Cheng Chen, Pu-Jen ...
ICTIR
2009
Springer
8 years 9 months ago
Training Data Cleaning for Text Classification
Abstract. In text classification (TC) and other tasks involving supervised learning, labelled data may be scarce or expensive to obtain; strategies are thus needed for maximizing t...
Andrea Esuli, Fabrizio Sebastiani
ICCV
2009
IEEE
8 years 9 months ago
Incremental Multiple Kernel Learning for object recognition
A good training dataset, representative of the test images expected in a given application, is critical for ensuring good performance of a visual categorization system. Obtaining ...
Aniruddha Kembhavi, Behjat Siddiquie, Roland Miezi...
HCI
2009
8 years 9 months ago
Considering User Knowledge in the Evaluation of Training System Usability
A variety of software-based systems are being used as training media. There is not, however, an accepted approach to evaluating the usability of these systems. Traditional usabilit...
Clint A. Bowers, Janis A. Cannon-Bowers, Talib S. ...
HCI
2009
8 years 9 months ago
Intelligent Agents for Training On-Board Fire Fighting
Simulation-based training in complex decision making often requires ample personnel for playing various roles (e.g. team mates, adversaries). Using intelligent agents may diminish ...
Karel van den Bosch, Maaike Harbers, Annerieke Heu...
EMNLP
2009
8 years 9 months ago
Domain adaptive bootstrapping for named entity recognition
Bootstrapping is the process of improving the performance of a trained classifier by iteratively adding data that is labeled by the classifier itself to the training set, and retr...
Dan Wu, Wee Sun Lee, Nan Ye, Hai Leong Chieu
EMNLP
2009
8 years 9 months ago
Discriminative Corpus Weight Estimation for Machine Translation
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...
DRR
2009
8 years 9 months ago
Using synthetic data safely in classification
When is it safe to use synthetic data in supervised classification? Trainable classifier technologies require large representative training sets consisting of samples labeled with...
Jean Nonnemaker, Henry Baird
ACL
2009
8 years 9 months ago
Stochastic Gradient Descent Training for L1-regularized Log-linear Models with Cumulative Penalty
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Yoshimasa Tsuruoka, Jun-ichi Tsujii, Sophia Anania...
books