Density estimation is one of the central problems in statistical inference and machine learning. Given a sample of observations, the goal of histogram density estimation is to find a piecewise constant density that describes the data best according to some pre-determined criterion. Although histograms are conceptually simple densities, they are very flexible and can model complex properties lik...

We regard histogram density estimation as a model selection problem. Our approach is based on the information-theoretic minimum description length (MDL) principle. MDLbased model selection is formalized via the normalized maximum likelihood (NML) distribution, which has several desirable optimality properties. We show how this approach can be applied for learning generic, irregular (variable-wi...

We are interested in model class selection. We want to compute a criterion which, given two competing model classes, chooses the better one. When learning Bayesian network structures from sample data, an important issue is how to evaluate the goodness of alternative network structures. Perhaps the most commonly used model (class) selection criterion is the marginal likelihood, which is obtained...

results 81 females aged 24 to 67 years (mean 43 ± 9.2) met the inclusion criteria and had adequate samples for histopathologic study. 28 (34%) patients had ml, 46 (56.8%) patients had nml and 7 (8.6%) had both ml and nml. rate of normal result, epithelial hyperplasia, fibrocystic changes, fibroadenoma, papilloma, atypical hyperplasia, mixed fibrocystic changes and atypical hyperplasia, ductal c...

Blacklegged ticks (n=12,606) were collected over four years (2007-2010) as part of a national passive tick surveillance program conducted in Canada by the National Microbiology Laboratory (NML) using the methods described previously (1). Adult I. scapularis were also collected by drag sampling: in 2008 from Itasca State Park, Camp Ripley and St. Croix State Park (n=56 per locality) in Minnesota...

Instruction Level Simulation has received big attention as it allows out-of-silicium test and hardware exploration. In this paper, we present GLISS2, the second release of a simulator generator based on the NML ADL. Thanks to the implementation of a set of optimization techniques (acceleration in memory emulation, caches for the decode step and blocking of instruction descriptors), we multiply ...

Nano Magnetic Logic (NML) has been attracting application in optical computing, nanodevice formation, and low power. In this paper nanoscale architecture such as the decoder, multiplexer, and comparator are implemented on perpendicular-nano magnetic logic (pNML) technology. All these architectures with the superiority of minimum complexity and minimum delay are pointed. The proposed architectur...

Bayesian networks are among most popular model classes for discrete vector-valued i.i.d data. Currently the most popular model selection criterion for Bayesian networks follows Bayesian paradigm. However, this method has recently been reported to be very sensitive to the choice of prior hyper-parameters [1]. On the other hand, the general model selection criteria, AIC [2] and BIC [3], are deriv...