Artificial Intelligence: Methodology, Systems, and Applications: 14th International Conference, AIMSA 2010, Varna, Bulgaria, September 8-10, 2010. ProceedingsDarina Dicheva, Danail Dochev The 14th International Conference on Artificial Intelligence: Methodology, Systems, Applications (AIMSA 2010) was held in Varna, Bulgaria, during September 8–10, 2010. The AIMSA conference series has provided a biennial forum for the presen- tion of artificial intelligence research and development since 1984. The conference covers the full range of topics in artificial intelligence (AI) and related disciplines and provides an ideal forum for international scientific exchange between Central/Eastern Europe and the rest of the world. The 2010 AIMSA edition continued this tradition. For AIMSA 2010, we decided to place special emphasis on the application and leverage of AI technologies in the context of knowledge societies where knowledge creation, accessing, acquiring, and sharing empower individuals and communities. A number of AI techniques play a key role in responding to these challenges. AI is - tensively used in the development of systems for effective management and flexible and personalized access to large knowledge bases, in the Semantic Web technologies that enable sharing and reuse of and reasoning over semantically annotated resources, in the emerging social Semantic Web applications that aid humans to collaboratively build semantics, in the construction of intelligent environments for supporting (human and agent) learning, etc. In building such intelligent applications, AI techniques are typically combined with results from other disciplines such as the social sciences, distributed systems, databases, digital libraries, information retrieval, service-oriented applications, etc. |
Other editions - View all
Common terms and phrases
activities agents algorithm analysis application approach approximation attributes classifier coalition combined compared complete Computer concepts considered consists constraints construction contains context corresponding dataset described direction distribution documents domain entity evaluation example experiments explore expression extraction function gene given graph Heidelberg identify implemented important improve individual instance integration Italy knowledge language learning limit machine mapping matrix means measures method negative networks neural nodes objects obtained ontology optimal particular patient performance personalized positive possible prediction presented problem proposed query reasoning recommendations References relations relevant representation represented retrieval selected Semantic similarity solution space stamps step structure Table task techniques tiles tion tutor University values variables vector weight