: This paper presents preliminary findings of an research project in which the research partners, academics and a telecommunication labour union, are attempting to understand, lear...
We show that, given data from a mixture of k well-separated spherical Gaussians in Rd, a simple two-round variant of EM will, with high probability, learn the parameters of the Ga...
Many events in news articles don't include time arguments. This paper describes two methods, one based on rules and the other based on statistical learning, to predict the un...
We consider online learning where the target concept can change over time. Previous work on expert prediction algorithms has bounded the worst-case performance on any subsequence ...
The availability of techniques for comparing descriptions has many applications in Artificial Intelligence, ranging from description selection to flexible matching, from instance...
Stefano Ferilli, Teresa Maria Altomare Basile, Nic...