Sciweavers

2861 search results - page 327 / 573
» Parallel Online Learning
Sort
View
110
Voted
ACL
2004
15 years 3 months ago
Unsupervised Sense Disambiguation Using Bilingual Probabilistic Models
We describe two probabilistic models for unsupervised word-sense disambiguation using parallel corpora. The first model, which we call the Sense model, builds on the work of Diab ...
Indrajit Bhattacharya, Lise Getoor, Yoshua Bengio
ICPP
2008
IEEE
15 years 8 months ago
Dynamic Meta-Learning for Failure Prediction in Large-Scale Systems: A Case Study
Despite great efforts on the design of ultra-reliable components, the increase of system size and complexity has outpaced the improvement of component reliability. As a result, fa...
Jiexing Gu, Ziming Zheng, Zhiling Lan, John White,...
ICPP
2007
IEEE
15 years 8 months ago
A Meta-Learning Failure Predictor for Blue Gene/L Systems
The demand for more computational power in science and engineering has spurred the design and deployment of ever-growing cluster systems. Even though the individual components use...
Prashasta Gujrati, Yawei Li, Zhiling Lan, Rajeev T...
EUROMICRO
1997
IEEE
15 years 6 months ago
What computer architecture can learn from computational intelligence-and vice versa
This paper considers whether the seemingly disparate fields of Computational Intelligence (CI) and computer architecture can profit from each others’ principles, results and e...
Ronald Moore, Bernd Klauer, Klaus Waldschmidt
ICML
2001
IEEE
16 years 3 months ago
Inducing Partially-Defined Instances with Evolutionary Algorithms
This paper addresses the issue of reducing the storage requirements on Instance-Based Learning algorithms. Algorithms proposed by other researches use heuristics to prune instance...
Josep Maria Garrell i Guiu, Xavier Llorà