Abstract
This paper first addresses the problem of excessively long neural network coding on high-dimensional data, and introduces the indirect coding neural evolution algorithm HyperNEAT, so that the neural network for high-dimensional data can also be coded with fewer genes, greatly reducing search space. Next, in order to solve the problem that the neuroevolution algorithm is difficult to effectively filter the features in the classification problem, this paper uses the feature-related information as the basis for the position of the input neuron. With the help of HyperNEAT, the advantage of the neuron geometric information can be effectively used, and an embedded feature is proposed. The selection method can improve the feature selection ability of the neuroevolution algorithm without increasing the time complexity.
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.
