4930 search results - page 34 / 986 » Learning minimal abstractions |
95
Voted
COLT
2005
Springer
15 years 6 months ago
2005
Springer
A general model is proposed for studying ranking problems. We investigate learning methods based on empirical minimization of the natural estimates of the ranking risk. The empiric...
CIE
2005
Springer
15 years 6 months ago
2005
Springer
Two properties of the Co-Spectrum of the Joint Spectrum tely many abstract structures are presented - a Minimal Pair type theorem and the existence of a Quasi-Minimal degree with r...
85
Voted
NIPS
2007
15 years 1 months ago
2007
This paper1 explores the use of a Maximal Average Margin (MAM) optimality principle for the design of learning algorithms. It is shown that the application of this risk minimizati...
135
click to vote
EMNLP
2006
15 years 1 months ago
2006
We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
58
Voted
JSYML
2006
15 years 12 days ago
2006
Abstract. We characterise strongly minimal groups interpretable in elementary extensions of compact complex analytic spaces.