Sciweavers

278 search results - page 22 / 56
» Strong Separation of Learning Classes
Sort
View
JSYML
2011
108views more  JSYML 2011»
14 years 9 months ago
Analytic equivalence relations and bi-embeddability
Abstract. Louveau and Rosendal [5] have shown that the relation of biembeddability for countable graphs as well as for many other natural classes of countable structures is complet...
Sy-David Friedman, Luca Motto Ros
99
Voted
ICML
2010
IEEE
15 years 3 months ago
Deep Supervised t-Distributed Embedding
Deep learning has been successfully applied to perform non-linear embedding. In this paper, we present supervised embedding techniques that use a deep network to collapse classes....
Martin Renqiang Min, Laurens van der Maaten, Zinen...
COGSCI
2006
62views more  COGSCI 2006»
15 years 2 months ago
Idiomatic Syntactic Constructions and Language Learning
This article explores the influence of idiomatic syntactic constructions (i.e., constructions whose phrase structure rules violate the rules that underlie the construction of othe...
Michael P. Kaschak, Jenny R. Saffran
SPATIALCOGNITION
2000
Springer
15 years 6 months ago
Influences of Context on Memory for Routes
Possible influences of contexts on memory for routes are investigated. Route knowledge was established by learning a route which was presented on a computer screen. Activation of k...
Sabine Schumacher, Karl Friedrich Wender, Rainer R...
122
Voted
JMLR
2010
123views more  JMLR 2010»
15 years 1 months ago
Maximum Relative Margin and Data-Dependent Regularization
Leading classification methods such as support vector machines (SVMs) and their counterparts achieve strong generalization performance by maximizing the margin of separation betw...
Pannagadatta K. Shivaswamy, Tony Jebara