Abstract
Node deletion and node addition are two important types of structure mutations for evolutionary neural network (ENN). How to select mutation type and mutation node has a crucial impact on the performance of ENN. In order to improve the convergence speed and classification accuracy of ENN, a heuristic structure mutation operator (HSMO) based on sensitivity was proposed. The output sensitivity of ENN with respect to each hidden node was analyzed with the derivative, and then the importance of the mutation type and the mutation node was measured jointly with the output sensitivity. The most important node was selected for deletion or addition. The experimental results with three classification problems show that the HSMO achieves better performance than the traditional structure mutation operator (TSMO) in terms of convergence speed and classification accuracy.
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.
