No abstract

This paper presents a family of probabilistic latent variable models that can be used for analysis of nonnegative data. We show that there are strong ties between nonnegative matrix factorization and this family, and provide some straightforward extensions which can help in dealing with shift invariances, higher-order decompositions and sparsity constraints. We argue through these extensions that the use of this approach allows for rapid development of complex statistical models for analyzing nonnegative data.

The preparation and characterization of oleogels structured by using a combination of a surface-active and a non-surfaceactive polysaccharide through an emulsion-templated approach is reported. Specifically, the oleogels were prepared by first formulating a concentrated oil-in-water emulsion, stabilized with a combination of cellulose derivatives and xanthan gum, followed by the selective evaporation of the continuous water phase to drive the network formation, resulting in an oleogel with a unique microstructure and interesting rheological properties, including a high gel strength, G' > 4000 Pa, shear sensitivity, good thixotropic recovery, and good thermostability.

In this paper we describe a technique that allows the extraction of multiple local shift-invariant features from analysis of non-negative data of arbitrary dimensionality. Our approach employs a probabilistic latent variable model with sparsity constraints. We demonstrate its utility by performing feature extraction in a variety of domains ranging from audio to images and video.

No abstract