Sciweavers

2934 search results - page 28 / 587
» Hypothesis Spaces for Learning
Sort
View
ALT
1999
Springer
15 years 6 months ago
Extended Stochastic Complexity and Minimax Relative Loss Analysis
We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An e ectiveperformance measure is the minimax re...
Kenji Yamanishi
APAL
2006
85views more  APAL 2006»
15 years 1 months ago
Compact spaces, elementary submodels, and the countable chain condition
Given a space X, J in an elementary submodel M of H(), define XM to be X M with the topology generated by {U M : U J M}. It is established, using anti-large-cardinals assumptio...
Lúcia R. Junqueira, Paul Larson, Franklin D...
88
Voted
ICML
2000
IEEE
16 years 2 months ago
Practical Reinforcement Learning in Continuous Spaces
William D. Smart, Leslie Pack Kaelbling
98
Voted
PRL
2008
97views more  PRL 2008»
15 years 1 months ago
Repairing self-confident active-transductive learners using systematic exploration
We consider an active learning game within a transductive learning model. A major problem with many active learning algorithms is that an unreliable current hypothesis can mislead...
Ron Begleiter, Ran El-Yaniv, Dmitry Pechyony