A method of general multi-concept learning based on cognitive model

Abstract

The increasing of the knowledge of mankind benefits from the concept learning. Based on the analysis of the common procedure of children's actions during recognizing the world, a cognitive model of concept learning is set up. A general multi-concept learning algorithm, a method of knowledge representation based on general rules, a logical structure in the forest shape, and a uniform data structure for storage are accordingly presented. Thus, a complete and more scientific knowledge acquisition and application case used for building knowledge base of many kinds of AI system based on knowledge is provided. Further more, with this method, a large scale knowledge base containing more extensive domains can be build. At last, comparing with some ontology knowledge bases, such as CYC, WordNet, NKI and so on, three different characteristics of this learning method are identified and the good application prospects are discussed. © Springer-Verlag Berlin Heidelberg 2012.