MAS 2012 Proceeding

Remarks on Qubit neuron-based quantum neural servo controller

Authors:   Kazuhiko Takahashi


This paper presents a servo-level controller using a quan- tum neural network and investigates its characteristics for control systems. A multi-layer quantum neural network that uses qubit neurons as an information processing unit is used to design three types of neural-network-based servo controllers a direct controller, parallel controller and self-tuning controller. Computational experiments to control a nonlinear discrete time plant are conducted in order to evaluate the learning performance and capa- bility of the quantum neural-network-based servo con- trollers. The results of the computational experiments confirm both the feasibility and effectiveness of the quan- tum neural-network-based servo controllers.

I3M  Scientific Sponsors

I3M  Industrial Sponsors

I3M  Media Sponsors