Coreferencing entities across documents in a large corpus enables advanced document understanding tasks such as question answering. This paper presents a novel cross document core...
Jian Huang 0002, Sarah M. Taylor, Jonathan L. Smit...
Following Tesauro’s work on TD-Gammon, we used a 4000 parameter feed-forward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of t...
We propose a simple yet potentially very effective way of visualizing trained support vector machines. Nomograms are an established model visualization technique that can graphica...
Aleks Jakulin, Martin Mozina, Janez Demsar, Ivan B...
This paper addresses exact learning of Bayesian network structure from data and expert's knowledge based on score functions that are decomposable. First, it describes useful ...
We present a method for parameter learning in relational Bayesian networks (RBNs). Our approach consists of compiling the RBN model into a computation graph for the likelihood fun...