Producing Modular Hybrid Rule Bases for Expert Systems
نویسندگان
چکیده
Neurules are a kind of hybrid rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding rule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural rule base is constructed, in contrast to existing connectionist rule bases. In this paper, we present a method for generating neurules from empirical data. We overcome the difficulty of the adaline unit to classify non-separable training examples by introducing the notion of ‘closeness’ between training examples and splitting each training set into subsets of ‘close’ examples.
منابع مشابه
WISA - A Modular and Hybrid Expert System for Machine and Plant Diagnosis
Expert systems are well known tools for diagnosis purposes in medicine and industry. One problem is the hard efford, to create the knowledge base. This article describes an expert system for industrial diagnosis and shows an efficient approach for the creation of the rule base, which is based on the reusage of knowledge modules. These knowledge modules are representants for assets like devices,...
متن کاملAn Attribute-rule Dependency Matrix Method and its Java Implementation for Rule-based Expert Systems Verification
Verification of knowledge bases is an important aspect of the development procedure of rule-based expert systems. The objective of verification is to assure producing a successful intelligent computer system that reaches correct recommendations. This research introduces an attribute-rule dependency matrix verification method and its associated Java implementation program. The method can help kn...
متن کاملConstructing Modular Hybrid Rule Bases for Expert Systems
Neurules are a kind of hybrid rules integrating neurocomputing and production rules. Each neurule is represented as an adaline unit. Thus, the corresponding neurule base consists of a number of autonomous adaline units (neurules). Due to this fact, a modular and natural knowledge base is constructed, in contrast to existing connectionist knowledge bases. In this paper, we present a method for g...
متن کاملIntegrating machine learning with knowledge-based systems
Computational learning systems attempt to improve performance with experience, according to some pre-de ned performance dimensions. Many such systems induce rule sets that function as simple knowledge bases (e.g., Quinlan, 1986). Simon (1983) argued that learning can be more e cient than programming for large knowledge-based systems. Thus, hybrid systems involving large knowledge bases may pro ...
متن کاملDetection of Anomalies of Hybrid Rule/Frame-based Expert Systems Using Coloured Petri Nets
High level Petri Nets have recently been used for many Artificial Intelligence applications, particularly for modelling traditional rule-based expert systems. The major effect is to facilitate the analysis of the knowledge inference during the reasoning process, and to support the system verification which increasingly becomes an integral part of expert system development. Nevertheless, there i...
متن کامل