Abstract. Experiments of neural network training procedure parallelization are conducted. Several styles of parallelization are described and compared, estimations of neural networ...
Abstract. This paper presents a method to compute metrics that predict maintainability of a system with respect to its event processing. The metrics reflect the complexity of event...
We develop a mixture-based approach to robust density modeling and outlier detection for experimental multivariate data that includes measurement error information. Our model is d...
Abstract. We address a location-allocation problem that requires deciding the location of a set of facilities, the allocation of customers to those facilities under facility capaci...
Despite significant progress in deformable model fitting over the last decade, the problem of efficient and accurate person-independentface fitting remains a challenging probl...