We estimate the location of a WLAN user based on radio signal strength measurements performed by the user's mobile terminal based on a probabilistic framework for solving the location estimation problem.Expand

The NML (normalized maximum likelihood) universal model has certain minmax optimal properties but it has two shortcomings: the normalizing coefficient can be evaluated in a closed form only for… Expand

We describe an experiment involving three artificial benchmark data sets to which a number of computer-assisted stemmatology methods were applied.Expand

We consider the problem of learning Bayesian network models in a non-informative setting, where the only available information is a set of observational data, and no background knowledge is available.Expand

We introduce a new probabilistic scoring criterion, the factorized normalized maximum likelihood, for learning Bayesian network structures from complete discrete data.Expand

We show that if the network structure satisfies a certain graph-theoretic condition, the corresponding conditional likelihood maximization problem is equivalent to logistic regression based on certain statistics of the data—different network structures leading to different statistics.Expand

We refine and extend an earlier minimum description length (MDL) denoising criterion for wavelet-based denoises and introduce soft thresholding inspired by predictive universal coding with weighted mixtures.Expand

We propose an efficient and parameter-free scoring criterion, the factorized conditional log-likelihood (fCLL), for learning Bayesian network classifiers.Expand

The important normalized maximum likelihood (NML) distribution is obtained via a normalization over all sequences of given length. It has two short-comings: the resulting model is usually not a… Expand