Spring Congress on Engineering and Technology

Remarks on Servo Controller Using Quantum Neural Network with Qubit Neurons

Kazuhiko Takahashi

Published May 1, 2012• 0 citations

Abstract

This paper presents the servo controller design of using a quantum 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 controller: the direct controller, the parallel controller and the self-tuning controller. Computational experiments to control the nonlinear discrete-time plant are conducted in order to evaluate the learning performance and the capability of the quantum neural controller. The results of the computational experiments confirm both the feasibility and effectiveness of the quantum neural controllers.

DOI: 10.1109/scet.2012.6341959

Related papers

Remarks on an adaptive-type parallel controller using quantum neural network with qubit neurons

Kazuhiko Takahashi

This paper presents an adaptive-type parallel controller based on a quantum 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 utilized to design the adaptive-type parallel controller that conducts the training of the quantum neural network as an online process. Computational experiments to control the single-input single-output nonlinear discrete time plant are conducted in order to evaluate the learning performance and capability of the adaptive-type quantum neural parallel controller. The results of the computational experiments confirm both the feasibility and the effectiveness of the adaptive-type quantum neural parallel controller.

International Conference on Intelligent Systems Design and Applications (ISDA)Nov 1, 20120 citations

Remarks on a quantum neural network using qubit neurons with application to control of a MIMO system

Kazuhiko Takahashi, Nagahashi Kazutaka, Yuka Wakaume +1 more

This study focused on a controller application of a quantum neural network, using qubit neurons as an information processing unit, and investigated its characteristics when controlling a multiple-input and multiple-output (MIMO) nonlinear system. Using a multilayer quantum neural network, a direct controller that conducts the online training of the quantum neural network was investigated. Computational experiments on the control of a MIMO non-linear discrete-time plant were conducted to evaluate the performance of the quantum neural network-based controller. The experimental results confirmed the effectiveness of the proposed quantum neural network-based controller and elucidated its characteristics.

International Conference on Advanced Mechatronic SystemsNov 1, 20160 citations

Controller Application of a Multi-Layer Quantum Neural Network with Qubit Neurons

Kazuhiko Takahashi, Motoki Kurokawa, Masafumi Hashimoto

This paper investigates a quantum neural network and discusses its application in control systems. A learning-type neural network-based controller that uses a multi-layer quantum neural network having qubit neurons as its information processing unit is proposed. Three learning algorithms; a back-propagation algorithm, a conjugate gradient algorithm and a real-coded genetic algorithm, are investigated to supervise the training of the multi-layer quantum neural network. To evaluate the learning performance and the capability of the quantum neural network-based controller, we conducted computational experiments for controlling a nonlinear discrete-time plant and a nonholonomic system - in this study a two-wheeled robot. The results of computational experiments confirm both the feasibility and the effectiveness of the quantum neural network-based controller and that the real-coded genetic algorithm is suitable for the learning method of the quantum neural network-based controller.

Journal of Advanced Mechanical Design Systems and ManufacturingJan 1, 201215 citations

Controller application of a multi-layer quantum neural network trained by a conjugate gradient algorithm

Kazuhiko Takahashi, Motoki Kurokawa, Masafumi Hashimoto

This paper investigates a quantum neural network and discusses its application to control systems. A learning-type neural control system that uses a multi-layer quantum neural network having qubit neurons as its information processing unit is proposed. A conjugate gradient algorithm is applied instead of the back-propagation algorithm for the supervised training of the multi-layer quantum neural network in order to improve learning performance. To evaluate the capability of the learning-type quantum neural control system, computational experiments are conducted for controlling a nonholonomic system - in this study a two-wheeled robot. Simulation results confirm both feasibility and robustness of the learning-type quantum neural control system.

Annual Conference of the IEEE Industrial Electronics Society (IECON)Nov 1, 20115 citations

The Design and Implementation of Quantum-Inspired Neural Networks

Yang Shu-yu

The approximation ability of neural networks plays an important role to the result when one uses neural networks to resolve problems.Unfortunately there is no ideal way to construct proper networks with strong approximation ability.A novel construction approach based on the multi-qubits controller-not gates is proposed for neural networks model in this paper.The proposed model consists of three layers where the hidden nodes are the quantum neurons and the output nodes are the common neurons.The quantum neuron consists of the quantum rotation gates and the multi-qubits controllednot gates.The overall memory of input sequences is captured from information feedback of target qubit from output to input in the multi-qubits controlled-not gate.The output of quantum neuron is obtained from the controlled relationship of the multi-qubits controlled-not gate.The L-M learning algorithms are designed in detail based on the basic principles of quantum computation.The features of input sequences can be effectively obtained in two ways of breadth and depth.The experimental results of solitaire forecast show that,when the number of input nodes is close to the length of sequences,the training set recognition rate of the proposed model increases about 8% than the common neural networks,which reveals the effectiveness of the quantum computation for enhancing the approximation capability of the common neural networks.

Journal of Signal ProcessingJan 1, 20140 citations

Algorithm and Application of the Quantum-Inspired Neural Network Model

Yang Shu-yu

To enhance the approximation and generalization ability of classical artificial neural networks,a quantum-inspired neural network model,whose input of each dimension is a discrete sequence,is proposed.This model concludes three layers,in which the hidden layer consists of quantum-inspired neurons,and the output layer consists of common neurons.The quantum-inspired neuron consists of the quantum rotation gates and the multi-qubits controlled-rotation gates.By using the information feedback of target qubit from output to input in multi-qubits controlled-rotation gate,the overall memory of input sequences is realized.The output of quantum-inspired neuron is obtained from the entanglements of multi-qubits in controlled-rotation gates.The learning algorithm is designed in detail according to the basic principles of quantum computation.The characteristics of input sequence can be effectively obtained by way ofbreadthanddepth.The simulation results show that,when the input nodes and the length of the sequence satisfy a certain relations,the proposed model is obviously superior to the common artificial neural networks.

Dianzi xuebaoJan 1, 20140 citations