Buggy software is a reality and automated techniques for discovering bugs are highly desirable. A specification describes the correct behavior of a program. For example, a file mus...
Traditional supervised visual learning simply asks annotators “what” label an image should have. We propose an approach for image classification problems requiring subjective...
: In this paper, we proposed a shallow syntactic knowledge description: constituent boundary representation and its simple and efficient prediction algorithm, based on different lo...
A multitask learning framework is developed for discriminative classification and regression where multiple large-margin linear classifiers are estimated for different predictio...
—This paper addresses the problem of simultaneous signal recovery and dictionary learning based on compressive measurements. Multiple signals are analyzed jointly, with multiple ...
Jorge Silva, Minhua Chen, Yonina C. Eldar, Guiller...