Sciweavers

2204 search results - page 98 / 441
» Agnostic active learning
Sort
View
136
Voted
NN
2000
Springer
167views Neural Networks» more  NN 2000»
15 years 4 months ago
Blind signal processing by the adaptive activation function neurons
The aim of this paper is to study an Information Theory based learning theory for neural units endowed with adaptive activation functions. The learning theory has the target to fo...
Simone Fiori
AIED
2005
Springer
15 years 10 months ago
What Do You Mean by to Help Learning of Metacognition?
Several computer-based learning support systems and methods help learners to master metacognitive activity. Which systems and methods are designed to eliminate which difficulties a...
Michiko Kayashima, Akiko Inaba, Riichiro Mizoguchi
ICML
2006
IEEE
16 years 5 months ago
Active sampling for detecting irrelevant features
The general approach for automatically driving data collection using information from previously acquired data is called active learning. Traditional active learning addresses the...
Sriharsha Veeramachaneni, Emanuele Olivetti, Paolo...
ICML
2009
IEEE
16 years 5 months ago
Uncertainty sampling and transductive experimental design for active dual supervision
Dual supervision refers to the general setting of learning from both labeled examples as well as labeled features. Labeled features are naturally available in tasks such as text c...
Vikas Sindhwani, Prem Melville, Richard D. Lawrenc...
ICCV
2011
IEEE
14 years 4 months ago
Actively Selecting Annotations Among Objects and Attributes
We present an active learning approach to choose image annotation requests among both object category labels and the objects’ attribute labels. The goal is to solicit those labe...
Adriana Kovashka, Sudheendra Vijayanarasimhan, Kri...