125 views119 votes15 years 5 months ago EMNLP 2008»
We present a study on how grammar binarization empirically affects the efficiency of the CKY parsing. We argue that binarizations affect parsing efficiency primarily by affecting ...
118 views123 votes15 years 3 months ago VLSISP 2008»
Abstract. The large amount of data generated by neuroprosthetic devices requires a high communication bandwidth for extra-cranial transmission, critically limiting the number and u...
136 views139 votes15 years 3 months ago TPDS 2002»
In this paper, an efficient algorithm to implement loop partitioning is introduced and evaluated. We start from results of Agarwal et al. [1] whose aim is to minimize the number of...
156 views124 votes15 years 5 months ago FLAIRS 2006»
We propose to improve the efficiency of genetic programming, a method to automatically evolve computer programs. We use graph-based data mining to identify common aspects of highl...
We present a novel, real-time disparity analysis frame work developed for immersive teleconferencing. This two-stage method computes a limited number of highly reliable disparitie...
: The growing interest in the MDA (Model-Driven Architecture) and MDD (Model-Driven Development) approaches has largely increased the number of tools and methods including code-gen...
A powerful combinational path sensitization engine is required for the efficient implementation of tools for test pattern generation, timing analysis, and delay fault testing. Path...
201 views164 votes15 years 5 months ago NIPS 2008»
Motor primitives or motion templates have become an important concept for both modeling human motor control as well as generating robot behaviors using imitation learning. Recent ...
A well-known problem that limits the practical usage of association rule mining algorithms is the extremely large number of rules generated. Such a large number of rules makes the...
Support vector machines (SVMs) excel at two-class discriminative learning problems. They often outperform generative classifiers, especially those that use inaccurate generative m...