Answers are grounded in this paper and cite their sources.
A Concept Tree is a structure for representing knowledge, where the trees are stored in a Concept Base. It sits between the highly distributed neural architectures and the distributed information systems, with the intention of bringing brain-like and computer systems closer together. Concept Trees can grow from unstructured or semi-structured sources when consistent sequences are presented. Each tree ideally represents a single cohesive concept and the trees can link with each other for navigation and semantic purposes. A consistent build process is managed through a 'counting rule' and mathematical basis that can normalise the database structure. This restricted structure can then be complimented and enriched by a more dynamic context. A number of tests have demonstrated the soundness of the architecture, which may be inherent in natural language. Two types of query language are also described that can answer knowledge-based questions and even enhance the query with new knowledge.
No takes yet. Share an insight, caveat, or question.
Kieran Greer (2019) studied this question.
Synapse has enriched 8 related papers. Consider them for comparative context: