Sciweavers

153 search results - page 28 / 31
» Semi-supervised learning by disagreement
Sort
View
NIPS
2003
13 years 11 months ago
Sensory Modality Segregation
Why are sensory modalities segregated the way they are? In this paper we show that sensory modalities are well designed for self-supervised cross-modal learning. Using the Minimiz...
Virginia R. de Sa
COGSCI
2007
109views more  COGSCI 2007»
13 years 9 months ago
Understanding the Emergence of Modularity in Neural Systems
: Modularity in the human brain remains a controversial issue, with disagreement over the nature of the modules that exist, and why, when and how they emerge. It is a natural assum...
John A. Bullinaria
TNN
2008
93views more  TNN 2008»
13 years 9 months ago
Towards the Optimal Design of Numerical Experiments
This paper addresses the problem of the optimal design of numerical experiments for the construction of nonlinear surrogate models. We describe a new method, called learner disagre...
S. Gazut, J.-M. Martinez, Gérard Dreyfus, Y...
GECCO
2008
Springer
137views Optimization» more  GECCO 2008»
13 years 11 months ago
Informative sampling for large unbalanced data sets
Selective sampling is a form of active learning which can reduce the cost of training by only drawing informative data points into the training set. This selected training set is ...
Zhenyu Lu, Anand I. Rughani, Bruce I. Tranmer, Jos...
ICML
2010
IEEE
13 years 11 months ago
Boosting Classifiers with Tightened L0-Relaxation Penalties
We propose a novel boosting algorithm which improves on current algorithms for weighted voting classification by striking a better balance between classification accuracy and the ...
Noam Goldberg, Jonathan Eckstein