Abstract
Traditionally, scientists preferred to design a neural network controller with sufficient neurons to satisfy realistic or simulational control requirements. Controllers derived from this methodology usually suffer tremendous training time and complicated neural network structure. Consequently, we decided to utilize ensemble theory which aims at replacing a complex object by effectively combining simpler analogical elements. In this paper, we build a neural network ensemble of multiple independent neural network controllers with an output fusion method based on k-nearest-neighbor (KNN)-like algorithm. implementing neural network ensemble on control problems, we successfully simulated the control output actuated by certain input signals. Comparison of this method with a traditional single neural network controller shows that the neural network controller ensemble does have a better performance on system converging speed and disturbance resistance.
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.