Prior-predictive value from fast growth simulations

Identifying predictive regions from fMRI with TV-`1 prior

“Decoding”, i.e. predicting stimulus related quantities from functional brain images, is a powerful tool to demonstrate differences between brain activity across conditions. However, unlike standard brain mapping, it offers no guaranties on the localization of this information. Here, we consider decoding as a statistical estimation problem and show that injecting a spatial segmentation prior le...

Prior-Posterior Predictive P-values

Adding Value Prior to Pulping: Bioproducts from Hemicellulose

The global trend for production of biofuels and bioproducts from renewable resources is currently steered by three important drivers: 1) increasing demand and prices of petroleumderived fuel; 2) increasing food needs; and 3) increasing greenhouse gas emissions. Biomass is the single renewable resource that has the potential to supplant the use of liquid transportation fuels now and help create ...

Fast Predictive Image Registration

We present a method to predict image deformations based on patch-wise image appearance. Specifically, we design a patch-based deep encoder-decoder network which learns the pixel/voxel-wise mapping between image appearance and registration parameters. Our approach can predict general deformation parameterizations, however, we focus on the large deformation diffeomorphic metric mapping (LDDMM) re...

Fast-Forwarding Crowd Simulations

The processing time to simulate crowds for games or simulations is a real challenge. While the increasing power of processing capacity is a reality in the hardware industry, it also means that more agents, better rendering and most sophisticated Artificial Intelligence (AI) methods can be used, so again the computational time is an issue. Despite the processing cost, in many cases the most inte...