In this work we present a novel method to model instance-level constraints within a clustering algorithm. Thereby, both similarity and dissimilarity constraints can be used coeval...
In this paper, we present a novel technique to automatically generate optimum classification cascades. Given a powerful classifier SF with satisfactory accuracy and a set of N cla...
Ezzat Ali El-Sherif, Sherif Abdelazeem, M. Fathy A...
This paper describes Orchid, a system that converts declarative mapping specifications into data flow specifications s) and vice versa. Orchid provides an abstract operator model t...
A new algorithm for training Restricted Boltzmann Machines is introduced. The algorithm, named Persistent Contrastive Divergence, is different from the standard Contrastive Diverg...
Object recognition forms a ubiquitous problem in digital image processing. The detection of robust image features of high distinctiveness is one important key in this regard. We p...