Workflows are modeled as hierarchically structured directed acyclic graphs in which vertices represent computational tasks, referred to as requests, and edges represent precedent c...
Nicolas G. Grounds, John K. Antonio, Jeffrey T. Mu...
Och's (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) models. The u...
The intersection of tree transducer-based translation models with n-gram language models results in huge dynamic programs for machine translation decoding. We propose a multipass,...
We study the stochastic machine replenishment problem, which is a canonical special case of closed multiclass queuing systems in Markov decision theory. The problem models the sche...
In this thesis we compare several machine learning techniques for evaluating external skeletal fixation proposals. We experimented in the context of dog bone fractures but the pot...
Ning Suo, Khaled Rasheed, Walter D. Potter, Dennis...