Sciweavers

2090 search results - page 54 / 418
» Learning with attribute costs
Sort
View
CVPR
2009
IEEE
15 years 4 months ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...
ML
2006
ACM
109views Machine Learning» more  ML 2006»
13 years 9 months ago
Cost curves: An improved method for visualizing classifier performance
Abstract This paper introduces cost curves, a graphical technique for visualizing the performance (error rate or expected cost) of 2-class classifiers over the full range of possib...
Chris Drummond, Robert C. Holte
GLOBECOM
2007
IEEE
14 years 3 months ago
Minimizing Distribution Cost of Distributed Neural Networks in Wireless Sensor Networks
Abstract—This paper presents a novel study on how to distribute neural networks in a wireless sensor networks (WSNs) such that the energy consumption is minimized while improving...
Peng Guan, Xiaolin Li
ICVS
2009
Springer
14 years 3 months ago
Incremental Video Event Learning
We propose a new approach for video event learning. The only hypothesis is the availability of tracked object attributes. The approach incrementally aggregates the attributes and r...
Marcos Zúñiga, François Br&ea...
ECCC
2006
96views more  ECCC 2006»
13 years 9 months ago
When Does Greedy Learning of Relevant Features Succeed? --- A Fourier-based Characterization ---
Detecting the relevant attributes of an unknown target concept is an important and well studied problem in algorithmic learning. Simple greedy strategies have been proposed that s...
Jan Arpe, Rüdiger Reischuk