We are developing a new problem-solving methodology based on a self-organization paradigm. To realize our future goal of self-organizing computational systems, we have to study co...
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring syste...
Wolfgang Macherey, Franz Josef Och, Ignacio Thayer...
Despite their superior performance for multimedia applications, vector processors have three limitations that hinder their widespread acceptance. First, the complexity and size of...
This paper presents a piece in a big mosaic which consists of formalisms and software packages for representing and reasoning with everyday temporal notions. The kernel of the mosa...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...