Sciweavers

1541 search results - page 124 / 309
» Learning to Diagnose by Doing
Sort
View
CI
2005
106views more  CI 2005»
14 years 9 months ago
Incremental Learning of Procedural Planning Knowledge in Challenging Environments
Autonomous agents that learn about their environment can be divided into two broad classes. One class of existing learners, reinforcement learners, typically employ weak learning ...
Douglas J. Pearson, John E. Laird
CVPR
2009
IEEE
1084views Computer Vision» more  CVPR 2009»
16 years 5 months ago
Describing Objects by their Attributes
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar ob...
Ali Farhadi, David A. Forsyth, Derek Hoiem, Ian En...
ICML
2006
IEEE
15 years 10 months ago
Feature value acquisition in testing: a sequential batch test algorithm
In medical diagnosis, doctors often have to order sets of medical tests in sequence in order to make an accurate diagnosis of patient diseases. While doing so they have to make a ...
Victor S. Sheng, Charles X. Ling
CORR
2010
Springer
275views Education» more  CORR 2010»
14 years 10 months ago
Dictionary Optimization for Block-Sparse Representations
Recent work has demonstrated that using a carefully designed dictionary instead of a predefined one, can improve the sparsity in jointly representing a class of signals. This has m...
Kevin Rosenblum, Lihi Zelnik-Manor, Yonina C. Elda...
SIGIR
2010
ACM
15 years 1 months ago
Combining coregularization and consensus-based self-training for multilingual text categorization
We investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the ...
Massih-Reza Amini, Cyril Goutte, Nicolas Usunier