In this paper we propose a parallel approach for the Kmeans Vector Quantization (VQ) algorithm used in a twostage Hidden Markov Model (HMM)-based system for recognizing handwritte...
Alceu de Souza Britto Jr., Paulo Sergio Lopes de S...
In this paper, we describe a compilation system that automates much of the process of performance tuning that is currently done manually by application programmers interested in h...
Nastaran Baradaran, Jacqueline Chame, Chun Chen, P...
Memory system bottlenecks limit performance for many applications, and computations with strided access patterns are among the hardest hit. The streams used in such applications h...
Abstract. We consider the problem of sequence prediction in a probabilistic setting. Let there be given a class C of stochastic processes (probability measures on the set of one-wa...
We explore a stacked framework for learning to predict dependency structures for natural language sentences. A typical approach in graph-based dependency parsing has been to assum...