We describe a novel family of PAC model algorithms for learning linear threshold functions. The new algorithms work by boosting a simple weak learner and exhibit complexity bounds...
We present MBoost, a novel extension to AdaBoost that extends boosting to use multiple weak learners explicitly, and provides robustness to learning models that overfit or are po...
This paper regards the recurrent linguistic rule bases. These systems are considered as relational models with several relations. Such representation allows to use relation algebr...
The class of weak parallel machines is interesting, because it contains some realistic parallel machine models, especially suitable for pipelined computations. We prove that a modi...
In this paper, we present a compositional boosting algorithm for detecting and recognizing 17 common image structures in low-middle level vision tasks. These structures, called &q...