Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
Automated grammar correction techniques have seen improvement over the years, but there is still much room for increased performance. Current correction techniques mainly focus on...
The emergence of heterogeneous many core architectures presents a unique opportunity for delivering order of magnitude performance increases to high performance applications by ma...
Recent work in supervised learning of term-based retrieval models has shown significantly improved accuracy can often be achieved via better model estimation [2, 10, 11, 17]. In ...
We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying featur...
Pei Yin, Irfan A. Essa, Thad Starner, James M. Reh...