Sciweavers

4128 search results - page 105 / 826
» Learning and using relational theories
Sort
View
CEC
2007
IEEE
15 years 4 months ago
A simple genetic algorithm for music generation by means of algorithmic information theory
— Recent large scale experiments have shown that the Normalized Information Distance, an algorithmic information measure, is among the best similarity metrics for melody classi...
Manuel Alfonseca, Manuel Cebrián, Alfonso O...
IJCNN
2000
IEEE
15 years 2 months ago
Extracting Distributed Representations of Concepts and Relations from Positive and Negative Propositions
Linear Relational Embedding (LRE) was introduced (Paccanaro and Hinton, 1999) as a means of extracting a distributed representation of concepts from relational data. The original ...
Alberto Paccanaro, Geoffrey E. Hinton
CE
2008
94views more  CE 2008»
14 years 10 months ago
Using mobile communication technology in high school education: Motivation, pressure, and learning performance
Motivation and pressure are considered two factors impacting vocational senior high school student learning. New communication technology, especially mobile communication technolo...
Pei-Luen Patrick Rau, Qin Gao, Li-Mei Wu
COLT
2007
Springer
15 years 4 months ago
How Good Is a Kernel When Used as a Similarity Measure?
Recently, Balcan and Blum [1] suggested a theory of learning based on general similarity functions, instead of positive semi-definite kernels. We study the gap between the learnin...
Nathan Srebro
JCIT
2008
112views more  JCIT 2008»
14 years 10 months ago
On the design of metric relations
Metric distances and the more general concept of dissimilarities are widely used tools in instance-based learning methods and very especially in the nearestneighbor classification...
Lluís Belanche, Jorge Orozco