Abstract
According to Zadeh's ideas, any fuzzy inference must be seen as an interpolation from the set of rules. The Compositional Rule of Inference makes this possible through a fuzzy relation being constructed by using an implication function, which introduces some reasonable properties to the reasoning (metaknowledge). In this paper we present an inference method that uses the neural network's ability of approximating any function. The basic idea is to construct a suitable neural network to learn the information contained in the rules, as well as the required metaknowledge from a specifically determined set of examples, and then to obtain the inference from a fact as an output of the networks, that is, to directly interpolate from rules.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
