We extend the VC theory of statistical learning to data dependent spaces of classifiers. This theory can be viewed as a decomposition of classifier design into two components; the...
Adam Cannon, J. Mark Ettinger, Don R. Hush, Clint ...
Several graph problems (e.g., steiner tree, connected domination, hamiltonian path, and isomorphism problem), which can be solved in polynomial time for distance-hereditary graphs...
—This paper describes a new approach to matching geometric structure in 2D point-sets. The novel feature is to unify the tasks of estimating transformation geometry and identifyi...
This paper studies the problem of sequence-to-sequence alignment, namely, establishing correspondences in time and in space between two different video sequences of the same dynami...
— The complexity of a design process or a design artifact substantially influences their performance. When evaluation of terms such as “design complexity” and its “quality...