Nonparametric Bayesian sparse factor models with application to gene expression modeling

A nonparametric Bayesian extension of Factor Analysis (FA) is proposed where observed data $\mathbf{Y}$ is modeled as a linear superposition, $\mathbf{G}$, of a potentially infinite number of hidden factors, $\mathbf{X}$. The Indian Buffet Process (IBP) is used as a prior on $\mathbf{G}$ to incorporate sparsity and to allow the number of latent features to be inferred. The model's utility for modeling gene expression data is investigated using randomly generated data sets based on a known sparse connectivity matrix for E. Coli, and on three biological data sets of increasing complexity.

Experimental and theoretical comparison between static and dynamic torsional soil tests

The dynamic properties of dry Leighton Buzzard sand have been investigated using a resonant column test apparatus. These data are compared with very low frequency cyclic tests on identical specimens of sand. The comparison indicates that the properties of dry sand are independent of frequency. A simple one-dimensional model of kinematic hardening plasticity is used to predict the dynamic behaviour of the sand. The input parameters for this model are based on the results of static tests. These may be conducted on standard laboratory equipment with only minor modifications. The predictions are in good agreement with the measured data.