Abstract. We formulate the problem of least squares temporal difference learning (LSTD) in the framework of least squares SVM (LS-SVM). To cope with the large amount (and possible ...
Abstract. Software security has become more important than ever. Unfortunately, still now, the security of a software system is almost always retrofitted to an afterthought. When s...
Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to ...
We present an approach for synthesizing transformations to enhance locality in imperfectly-nested loops. The key idea is to embed the iteration space of every statement in a loop ...
This paper presents an extensive empirical evaluation of an interprocedural parallelizing compiler, developed as part of the Stanford SUIF compiler system. The system incorporates...
Mary W. Hall, Saman P. Amarasinghe, Brian R. Murph...