In this paper, we develop a high-performance GPU kernel for one of the most popular dense linear algebra operations, the matrixvector multiplication. The target hardware is the most recent Nvidia Tesla 20-series (Fermi architecture), which is designed from the ground up for scientific computing. We show that it is essentially a matter of fully utilizing the fine-grained parallelism of the many-...

In this paper we propose a model that combines the strengths of RNNs and SGVB: the Variational Recurrent Auto-Encoder (VRAE). Such a model can be used for efficient, large scale unsupervised learning on time series data, mapping the time series data to a latent vector representation. The model is generative, such that data can be generated from samples of the latent space. An important contribu...

We present the GlobalizeBVP algorithm for the computation of two-dimensional stable and unstable manifolds of a vector field. Specifically, we use the collocation routines of Auto to solve boundary problems that are used during the computation to find the next approximate geodesic level set on the manifold. The resulting implementation is numerically very stable and well suited for systems with...

Electric load forecasting is an important issue for a power utility, associated with the management of daily operations such as energy transfer scheduling, unit commitment, and load dispatch. Inspired by strong non-linear learning capability of support vector regression (SVR), this paper presents a SVR model hybridized with the empirical mode decomposition (EMD) method and auto regression (AR) ...

Leishmaniasis is a vector-borne disease caused by protozoan parasites of the genus Leishmania. Our knowledge of protein phosphatases (PPs) and their implication in signaling events is very limited. Here we report the expression, characterization and mutagenesis analysis of a novel protein phosphatase 5 (PP5) in Leishmania major. Recombinant PP5 is a bona fide phosphatase and is enzymatically ac...

In this paper, a new scheme that merges color and texture information for bark image recognition is proposed. The feature vectors concerning color and texture are extracted using the multiresolution wavelet. In addition, the application of these features for bark classification using radial basis probabilistic network (RBPNN) and support vector machine (SVM) has been introduced. Finally, experi...

ERRATUM: It has come to our attention that there was a flaw in our use of Socher et al. (2011)’s recursive auto-encoder (RAE). Whereas the original version of this paper used one and the same pair of compositional matrices W (1),W (2) for composing word vectors from all involved sources, in this corrected version we retrained the RAE’s compositional matrices for each word vector source. This so...

The chemical shift is sensitive to changes in the local environments and can report the structural changes. The structure information of a protein can be represented by the average chemical shifts (ACS) composition, which has been broadly applied for enhancing the prediction accuracy in protein subcellular locations and protein classification. However, different kinds of ACS composition can sol...