Recent versions of microprocessors exhibit performance characteristics for 32 bit floating point arithmetic (single precision) that is substantially higher than 64 bit floating point arithmetic (double precision). Examples include the Intel’s Pentium IV and M processors, AMD’s Opteron architectures and the IBM’s Cell Broad Engine processor. When working in single precision, floating point opera...

In this paper the refinement procedure of informal requirements in the context of an earlier proposed systematic procedure for logic controller design as sequential function chart (SFC) is described in detail. The use of two data formats is proposed: dependency charts (DC) and function tables (FT) that support hierarchy and modularization and are refined iteratively until a final degree of deta...

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task. We extensively evaluate the proposed model on machine translation (En↔De and En↔Ro) and image caption generation, and observe that...

Iterative refinement clustering algorithms (e.g. K-Means, EM) converge to one of numerous local minima. It is known that they are especially sensitive to initial conditions. We present a procedure for computing a refined starting condition from a given initial one that is based on an efficient technique for estimating the modes of a distribution. The refined initial starting condition leads to ...

We present a CPU efficient protocol for refinement of protein structures in a thin layer of explicit solvent and energy parameters with completely revised dihedral angle terms. Our approach is suitable for protein structures determined by theoretical (e.g., homology modeling or threading) or experimental methods (e.g., NMR). In contrast to other recently proposed refinement protocols, we put a ...

Three iterative refinement schemes are studied for approximating the solutions of linear weakly singular Fredholm integral equations of the second kind. The rates of convergence and computational costs of the three schemes are studied and compared with the classical approach by applying them respectively to: (i) a sparse linear system associated with an integral equation modelling a real life A...

We have applied structured adaptive mesh refinement techniques to the solution of the LDA equations for electronic structure calculations. Local spatial refinement concentrates memory resources and numerical effort where it is most needed, near the atomic centersand in regions of rapidly varying charge density. The structured grid representation enables us to employ efficient iterative solver t...

Variational methods that rely on a recognition network to approximate the posterior of directed graphical models offer better inference and learning than previous methods. Recent advances that exploit the capacity and flexibility in this approach have expanded what kinds of models can be trained. However, as a proposal for the posterior, the capacity of the recognition network is limited, which...

In this paper we present the development process of NLP-QT, a question treebank that will be used for data-driven parsing in the context of a domain-specific QA system for querying NLP resource metadata. We motivate the need to build NLP-QT as a resource in its own right, by comparing the Penn Treebank-style annotation scheme used for QuestionBank (Judge et al., 2006) with the modified NP annot...

In this paper we review the effect of two high-performance techniques for the solution of matrix equations arising in control theory applications on CPU-GPU platforms, in particular advanced optimization via look-ahead and iterative refinement. Our experimental evaluation on the last GPU-generation from NVIDIA, “Kepler”, shows the slight advantage of matrix inversion via Gauss-Jordan eliminatio...