Sciweavers

127 search results - page 1 / 26
» Online Methods for Multi-Domain Learning and Adaptation
Sort
View
EMNLP
2008
13 years 6 months ago
Online Methods for Multi-Domain Learning and Adaptation
NLP tasks are often domain specific, yet systems can learn behaviors across multiple domains. We develop a new multi-domain online learning framework based on parameter combinatio...
Mark Dredze, Koby Crammer
ACL
2012
11 years 7 months ago
Fast Online Training with Frequency-Adaptive Learning Rates for Chinese Word Segmentation and New Word Detection
We present a joint model for Chinese word segmentation and new word detection. We present high dimensional new features, including word-based features and enriched edge (label-tra...
Xu Sun, Houfeng Wang, Wenjie Li
COLT
2010
Springer
13 years 3 months ago
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradie...
John Duchi, Elad Hazan, Yoram Singer
NIPS
2004
13 years 6 months ago
Stable adaptive control with online learning
Learning algorithms have enjoyed numerous successes in robotic control tasks. In problems with time-varying dynamics, online learning methods have also proved to be a powerful too...
Andrew Y. Ng, H. Jin Kim
APPINF
2003
13 years 6 months ago
Evolving High-Dimensional, Adaptive Camera-based Speed Sensors
This paper reviews some attempts that exploit a phenomenon, also known as motion parallax, to estimate the distance of closest approach of a moving object. Despite their success, ...
Ralf Salomon