Sorry, you need to enable JavaScript to visit this website.

This paper studies compression techniques for parallel in-memory sparse tensor algebra. We find that applying simple existing compression schemes can lead to performance loss in some cases. To resolve this issue, we introduce an optimized algorithm for processing compressed inputs that can improve both the space usage as well as the performance compared to uncompressed inputs. We implement the compression techniques on top of a suite of sparse matrix algorithms generated by taco, a compiler for sparse tensor algebra.

Partial occlusions in face images pose a great problem for most face recognition algorithms due to the fact that most of these algorithms mainly focus on solving a second order loss function, e.g., mean square error (MSE), which will magnify the effect from occlusion parts. In this paper, we proposed a kernel non-second order loss function for sparse representation (KNS-SR) to recognize or restore partially occluded facial images, which both take the advantages of the correntropy and the non-second order statistics measurement.

The orthogonal matching pursuit (OMP) is an important sparse approximation algorithm to recover sparse signals from compressed measurements. However, most MP algorithms are based on the mean square error(MSE) to minimize the recovery error, which is suboptimal when there are outliers.

In recent history, dictionary learning (DL) methods have been successfully used for analyzing multi-subject functional magnetic resonance imaging. These algorithms try to learn group-level spatial activation maps (SM) or voxel time courses (TC) from temporally or spatially concatenated fMRI datasets respectively. However, in multi-subject fMRI studies, we are interested in both group-level TCs as well as SMs.

In this paper, three sparse models for the human auditory system are proposed. Biological studies shows that the haircells in the inner ear of the auditory system generate sparse codes from the output of cochlea filterbank. Here, we employ two mathematical sparse representation methods, which are Orthogonal Matching Pursuit (OMP) and K Singular Value Decomposition (K-SVD), in three different strategies for sparse representation of the output of cochlea filterbank that is modeled by a Gammatone filterbank.