Sciweavers

866 search results - page 42 / 174
» Extension of the direct optimization algorithm for noisy fun...
Sort
View
ML
2006
ACM
110views Machine Learning» more  ML 2006»
13 years 7 months ago
Classification-based objective functions
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
Michael Rimer, Tony Martinez
ACL
2009
13 years 5 months ago
Optimizing Word Alignment Combination For Phrase Table Training
Combining word alignments trained in two translation directions has mostly relied on heuristics that are not directly motivated by intended applications. We propose a novel method...
Yonggang Deng, Bowen Zhou
ECCV
2006
Springer
14 years 9 months ago
Statistical Priors for Efficient Combinatorial Optimization Via Graph Cuts
Abstract. Bayesian inference provides a powerful framework to optimally integrate statistically learned prior knowledge into numerous computer vision algorithms. While the Bayesian...
Daniel Cremers, Leo Grady
NETWORK
2010
122views more  NETWORK 2010»
13 years 2 months ago
Betweenness centrality and resistance distance in communication networks
In this article we report on applications and extensions of weighted graph theory in the design and control of communication networks. We model the communication network as a weig...
Ali Tizghadam, Alberto Leon-Garcia
PAMI
2007
186views more  PAMI 2007»
13 years 7 months ago
Value-Directed Human Behavior Analysis from Video Using Partially Observable Markov Decision Processes
—This paper presents a method for learning decision theoretic models of human behaviors from video data. Our system learns relationships between the movements of a person, the co...
Jesse Hoey, James J. Little