Abstract
Intelligent functions and learning are important issues, which are needed in the application fields. Recently, these technologies are extensively studied and developed using threshold neural networks. The nearest neighbor relations are proposed for the basis of the generation of functions and learning. First, the these relations are shown to have minimal information for the discrimination and to be the basis of the inherited information for threshold functions. Second, for the Chow parameter problems, we developed fundamental schemes of the nearest neighbor relations and performed their analysis for the Chow parameters. The sequential generation of the Chow parameters is proposed which is caused by small changes of the connecting weights in threshold neurons.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.