Sciweavers

2623 search results - page 224 / 525
» Universal Learning Theory
Sort
View
ICML
2009
IEEE
16 years 7 months ago
Learning kernels from indefinite similarities
Similarity measures in many real applications generate indefinite similarity matrices. In this paper, we consider the problem of classification based on such indefinite similariti...
Yihua Chen, Maya R. Gupta, Benjamin Recht
ICML
2009
IEEE
16 years 7 months ago
Archipelago: nonparametric Bayesian semi-supervised learning
Semi-supervised learning (SSL), is classification where additional unlabeled data can be used to improve accuracy. Generative approaches are appealing in this situation, as a mode...
Ryan Prescott Adams, Zoubin Ghahramani
ICML
2000
IEEE
16 years 7 months ago
Learning Subjective Functions with Large Margins
In manyoptimization and decision problems the objective function can be expressed as a linear combinationof competingcriteria, the weights of whichspecify the relative importanceo...
Claude-Nicolas Fiechter, Seth Rogers
IAT
2008
IEEE
16 years 1 months ago
Formalizing Multi-state Learning Dynamics
This paper extends the link between evolutionary game theory and multi-agent reinforcement learning to multistate games. In previous work, we introduced piecewise replicator dynam...
Daniel Hennes, Karl Tuyls, Matthias Rauterberg
ECML
2000
Springer
15 years 11 months ago
Metric-Based Inductive Learning Using Semantic Height Functions
In the present paper we propose a consistent way to integrate syntactical least general generalizations (lgg's) with semantic evaluation of the hypotheses. For this purpose we...
Zdravko Markov, Ivo Marinchev