Finite mixture models are statistical models which appear in many problems in statistics and machine learning. In such models it is assumed that data are drawn from random probability measures, called mixture components, which are themselves drawn from a probability measure P over probability measures. When estimating mixture models, it is common to make assumptions on the mixture components, s...

We consider unsupervised estimation of mixtures of discrete graphical models, where the class variable corresponding to the mixture components is hidden and each mixture component over the observed variables can have a potentially different Markov graph structure and parameters. We propose a novel approach for estimating the mixture components, and our output is a tree-mixture model which serve...

A simplified approach to the problem of determining the relative proportion of minerals in a mixture from a reflectance spectrum of the mixture is presented. Fundamental to this approach is a priori information concerning reflectance spectra of the minerals in the mixture and some estimate of the particle sizes of the mixture components. Reflectance spectra of intimate mixtures are a systematic...

This application note demonstrates the utility of the DOSY package in the VnmrJ 3.1 software for both 2D and 3D HR-DOSY analysis of complex mixtures, by first elucidating the presence of two components in an epoxy mixture (2D), and then proving that a minority component in a protein mixture was in fact a smaller derivative of the major component (3D).

This application note demonstrates the utility of the DOSY package in the VnmrJ 3.1 software for both 2D and 3D HR-DOSY analysis of complex mixtures, by first elucidating the presence of two components in an epoxy mixture (2D), and then proving that a minority component in a protein mixture was in fact a smaller derivative of the major component (3D).

Odor mixture perception can be configural (the mixture is qualitatively different from the components) or elemental (the components are recognizable). Some have argued that configural properties are dependent on chemical similarity and possible overlap at the receptor level. The authors show that a binary mixture in which both components activate the same receptor (17) has a configural odor, wh...

Responses from hamster parabrachial nuclei neurons to stimulation of the anterior tongue with sucrose, NaCl, HCI, quinine hydrochloride, and the six two-component mixtures of these stimuli were recorded . A cell's response to a mixture approached its response to the mixture's more effective component in the majority of cases, but was sometimes greater or smaller than this response . The best pr...

Individual odorants activate only a small fraction of mitral cells in the mouse main olfactory bulb (MOB). Odor mixtures are represented by a combination of activated mitral cells, forming reproducible activation maps in the olfactory bulb. However, how the activation of a cohort of narrowly tuned mitral cells by odor mixtures is read out synaptically by neurons in higher-level olfactory struct...