An estimation of the number of multiplication and addition operations fortraining articial neural networks by means of consecutive and parallel algorithmson a computer cluster is carried out. The evaluation of the eciency of thesealgorithms is developed. The multilayer perceptron, the Volterra...

This paper describes parallel algorithms for training articial neural networks.Possible levels of parallelity are presented. Experiments for checking the efficiencyof algorithms are discussed.[...]

Expert-driven business process management is an establishedmeans for improving efficiency of organizational knowledge work.Implicit procedural knowledge in the organization is made explicit bydening processes. This approach is not applicable to individual knowledgework due to its high complexity...

One of the key factors that hinders integration of distributed, heterogeneousinformation systems is the lack of a formal basis for modeling the complex, structuredknowledge that is to be exchanged. To alleviate this situation, we present anapproach based on core ontologies. Core ontologies are...

Knowledge compilation is a common technique for propositionallogic knowledge bases. A given knowledge base is transformedinto a normal form, for which queries can be answered efficiently. Thisprecompilation step is expensive, but it only has to be performed once.We apply this technique to...

Ontologies play an important role in knowledge representationfor sharing information and collaboratively developing knowledgebases. They are changed, adapted and reused in different applicationsand domains resulting in multiple versions of an ontology. The comparisonof different versions and the...

With the Multimedia Metadata Ontology (M3O), we havedeveloped a sophisticated model for representing among others the annotation,decomposition, and provenance of multimedia metadata. Thegoal of the M3O is to integrate the existing metadata standards andmetadata formats rather than replacing...

Existing tools for generating application programming interfaces(APIs) for ontologies lack sophisticated support for mapping thelogics-based concepts of the ontology to an appropriate object-orientedimplementation of the API. Such a mapping has to overcome the fundamentaldierences between the...