Please use this identifier to cite or link to this item:
|Title:||Integrated shell for developing connectionist expert systems||Authors:||Quah, Tong-Seng
|Issue Date:||1993||Citation:||Quah, Tong-Seng,Tan, Chew-Lim,Teh, Hoon-Heng,Shen, ZuLiang (1993). Integrated shell for developing connectionist expert systems. Proceedings of the International Joint Conference on Neural Networks 3 : 2889-2892. ScholarBank@NUS Repository.||Abstract:||This paper presents a prototype shell for developing neural network expert systems. The shell, structured around the concept of Neural Logic Network Element (netel), is aimed at preserving semantic structure of the expert system rules whilst incorporating learning capability of neural networks into the inferencing mechanism. Using this architecture, every rule of the knowledge base is represented by a netel. These netels are dynamically linked up to form the rule-tree during inferencing process. The system is also able to adjust its inference strategy according to different users and situations. An editor and a rule-base system alike user interface shell is provided to enable easy maintenance of the netel knowledge base. The prototype shell is used to build an advisory expert system for bond trading. The system yields promising results, thus demonstrated strengths of the above-mentioned architecture.||Source Title:||Proceedings of the International Joint Conference on Neural Networks||URI:||http://scholarbank.nus.edu.sg/handle/10635/111259||ISBN:||0780314212|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.