Hierarchical Knowledge Representation to Approximate Functions
This paper presents a practical example of a system based on neural networks that permits to bnild a conceptual hierarchy. This neural system classifies an input pattern as an dement of each different category or snbcategory that the system has, until an exhaustive classification Is obtained. The proposed nenral system to not a hierarchy of neural networks, it establishes relationships among all the different nenral networks in order to transmit the nenral activation when an external stimulus to presented to the system. Each nenral network Is in charge of the inpnt pattern recognition to any prototyped class or category, and also of transmitting the activation to other nenral networks to be able to continue with the classification. Therefore, the communication of the neural activation in the system depends on the output of each one of the nenral networks, so as the functional links established among the different networks to represent the underlying conceptual hierarchy.
Luis Fernando de Mingo Fernando Arroyo Juan Castellanos
Escuela Universitaria de Informática Universidad Politécnica de Madrid Crta. de Valencia km. 7 - 280 Facultad de Informática Universidad Politécnica de Madrid Boadilla del Monte - 28660 Madrid, Spain
国际会议
Firth IEEE International Conference on Cognitive Informatics(第五届认知信息国际会议)
北京
英文
261-267
2006-07-17（万方平台首次上网日期，不代表论文的发表时间）