Sciweavers

3502 search results - page 232 / 701
» From Machine Learning to Machine Reasoning
Sort
View
AAAI
1993
15 years 7 months ago
Learning Object Models from Appearance
We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem a...
Hiroshi Murase, Shree K. Nayar
ML
2010
ACM
135views Machine Learning» more  ML 2010»
15 years 1 months ago
Multi-domain learning by confidence-weighted parameter combination
State-of-the-art statistical NLP systems for a variety of tasks learn from labeled training data that is often domain specific. However, there may be multiple domains or sources o...
Mark Dredze, Alex Kulesza, Koby Crammer
ECCV
2008
Springer
16 years 8 months ago
Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks
Abstract. Building visual recognition models that adapt across different domains is a challenging task for computer vision. While feature-learning machines in the form of hierarchi...
Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xi...
ICRA
2009
IEEE
188views Robotics» more  ICRA 2009»
16 years 1 months ago
Learning sound location from a single microphone
Abstract— We consider the problem of estimating the incident angle of a sound, using only a single microphone. The ability to perform monaural (single-ear) localization is import...
Ashutosh Saxena, Andrew Y. Ng
ALT
2009
Springer
15 years 11 months ago
The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses
In this paper the sequential prediction problem with expert advice is considered for the case when the losses of experts suffered at each step can be unbounded. We present some mo...
Vladimir V. V'yugin