New methods to generate hard random problem instances have driven progress on algorithms for deduction and constraint satisfaction. Recently Achlioptas et al. (AAAI 2000) introduc...
Henry A. Kautz, Yongshao Ruan, Dimitris Achlioptas...
Information Systems (IS) design research tends to emphasise the development of new methods (normative research), while addressing the evaluation of methods in only a limited fashi...
Previous work demonstrated that web counts can be used to approximate bigram frequencies, and thus should be useful for a wide variety of NLP tasks. So far, only two generation ta...
We propose a novel a framework for deriving approximations for intractable probabilistic models. This framework is based on a free energy (negative log marginal likelihood) and ca...
Estimating insurance premia from data is a difficult regression problem for several reasons: the large number of variables, many of which are discrete, and the very peculiar shape...
Nicolas Chapados, Yoshua Bengio, Pascal Vincent, J...