首页>
外国专利>
A NEUROCOGNITIVE KNOWLEDGE NETWORK FACILITATES THE ENHANCEMENT OF THE COGNITIVE ABILITIES OF THE EXISTING KNOWLEDGE SYSTEMS FOR INFORMATION PROCESSING.
A NEUROCOGNITIVE KNOWLEDGE NETWORK FACILITATES THE ENHANCEMENT OF THE COGNITIVE ABILITIES OF THE EXISTING KNOWLEDGE SYSTEMS FOR INFORMATION PROCESSING.
展开▼
机译：神经认知知识网络有助于增强现有信息处理知识系统的认知能力。
展开▼
页面导航
摘要
著录项
相似文献
摘要
Researchers in the field of Artificial Intelligence and Cognition have tried many models earlier, to simulate conceptual learning property, which can not only encode and retrieve knowledge efficiently but can also be consistent and scalable at all times. Till now knowledge-based system and Semantic web had been developed which mainly uses Ontologies to represent knowledge. Ontology development faces many challenges. To mention few of them here namely they cannot model events that are relationships between concepts and even they fail to distinguish between different relationships. Also, Ontologies cannot model events that change with time and the facts that change over time. Most important of all, the difference in representation of domain ontologies makes it hard to integrate domain ontologies. Semantic Web also imposes many challenges. To overcome the drawback of the Ontology development and Semantic Web, our invention put forward a neurocognitive knowledge network model (NCKM) with autonomous processing nodes that are linked using multilateral links. The autonomous node is a four-quadrant node that is referred to as Knowledge Network Node (KNN) where each quadrant plays an important role during the process of knowledge embedding and retrieval. NCKM links provide for weight gradation, as a knowledge thread is traversed and also provides for dynamic link weight formation. The dynamic link weight property super-imposed with the weight gradation property provides for self-directivity and self-organization of the network that tends to impose learning within the NCKM. The NCKM system brings in artificial intelligence processing capabilities as an inherent property of its nodes with intelligent linking. NCKM exhibit Hebbian learning along with the equilibrium process which in turn provides a stable learned, scalable and reconfigurable network.
展开▼
