The formal architecture of Lexical Functional Grammar offers a particular formal device, the structural correspondence, for modularizing the mapping between the surface forms of a...
Many traditional methods for shape classification involve
establishing point correspondences between shapes to
produce matching scores, which are in turn used as similarity
meas...
We study the problem of learning kernel machines transductively for structured output variables. Transductive learning can be reduced to combinatorial optimization problems over a...
Insights into branch predictor organization and operation can be used in architecture-aware compiler optimizations to improve program performance. Unfortunately, such details are ...
Bayesian belief networks have grown to prominence because they provide compact representations of many domains, and there are algorithms to exploit this compactness. The next step...