Sciweavers

728 search results - page 50 / 146
» Concept Maps and Learning Objects
Sort
View
ML
2000
ACM
157views Machine Learning» more  ML 2000»
13 years 8 months ago
A Multistrategy Approach to Classifier Learning from Time Series
We present an approach to inductive concept learning using multiple models for time series. Our objective is to improve the efficiency and accuracy of concept learning by decomposi...
William H. Hsu, Sylvian R. Ray, David C. Wilkins
ICASSP
2011
IEEE
13 years 16 days ago
Increasing discriminative capability on MAP-based mapping function estimation for acoustic model adaptation
In this study, we propose increasing discriminative power on the maximum a posteriori (MAP)-based mapping function estimation for acoustic model adaptation. Based on the effective...
Yu Tsao, Ryosuke Isotani, Hisashi Kawai, Satoshi N...
ICML
2010
IEEE
13 years 10 months ago
Non-Local Contrastive Objectives
Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabili...
David Vickrey, Cliff Chiung-Yu Lin, Daphne Koller
HICSS
2010
IEEE
187views Biometrics» more  HICSS 2010»
13 years 10 months ago
Navigation Support for Mobile Learning
Mobile learning exposes learning to the natural environment. If this environment is large, the learners have to navigate to find the learning objects or to explore the environment...
Christoph Göth, Gerhard Schwabe
IROS
2008
IEEE
111views Robotics» more  IROS 2008»
14 years 3 months ago
Mapping and planning under uncertainty in mobile robots with long-range perception
— Recent advances in self-supervised learning have enabled very long-range visual detection of obstacles and pathways (to 100 hundred meters or more). Unfortunately, the category...
Pierre Sermanet, Raia Hadsell, Marco Scoffier, Urs...