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

Takahashi, Kazuhiko; Kurokawa, Motoki; Hashimoto, Masafumi

doi:10.1109/iecon.2011.6119677

Cited by 5 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A quantum neural network that utilizes the qubit 1 neurons as an information processing unit was proposed in [7], where the qubit neuron model is one in which the neuron states are connected to the quantum states and the transitions between neuron states are based on operations derived from quantum logic gates. The high learning ability of the quantum neural network with qubit neurons was demonstrated in several basic benchmark tests and applications [8], [9], [10], [11]. During the past quarter of the century, many studies about the application of both the flexibility and the learning ability of neural networks to control systems have been conducted worldwide [12].…”

Section: Introductionmentioning

confidence: 99%

Remarks on Servo Controller Using Quantum Neural Network with Qubit Neurons

Takahashi

2012

2012 Spring Congress on Engineering and Technology

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

Remarks on Servo Controller Using Quantum Neural Network with Qubit Neurons

Takahashi

2012

2012 Spring Congress on Engineering and Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…A quantum neural network which utilizes qubit-inspired neurons as information processing units has been proposed, and its high learning capability has been confirmed in several benchmark tests and applications (Kouda et al, 2005) (Zhou et al, 2006). As a servo-level controller application which uses the quantum neural network with qubit neurons, a direct controller in which the output of the quantum neural network is the control input of the object plant has been proposed and its feasibility demonstrated (Takahashi et al, 2011). This paper proposes an adaptive-type self-tuning controller by using a quantum neural network, and investigates its characteristics for control systems.…”

Section: Introductionmentioning

confidence: 99%

Remarks on an Adaptive-type Self-tuning Controller using Quantum Neural Network with Qubit Neurons

Takahashi¹,

Shiotani²,

Hashimoto³

2013

Proceedings of the 10th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

This paper presents a self-tuning controller based on a quantum neural network and investigates the controller's characteristics for control systems. A multi-layer quantum neural network which uses qubit neurons as an information processing unit is utilized to design an adaptive-type self-tuning controller which conducts the training of the quantum neural network as an online process. As an example of designing the self-tuning controller, either a proportional integral derivative controller or a fuzzy logic controller is utilized as a conventional controller for which parameters are tuned by the quantum neural network. To evaluate the learning performance and capability of the adaptive-type quantum neural self-tuning controller, we conduct computational experiments to control the single-input single-output non-linear discrete time plant. The results of the computational experiments confirm both feasibility and effectiveness of the proposed self-tuning controller.

show abstract

“…After the concept of quantum neural computing was originally presented by Kak [10], various studies of quantum neural networks have been conducted because quantum neural networks are expected to have several advantages of solving classically intractable problems that are hard to treat by conventional neural networks [11]. A quantum neural network that utilizes qubit neurons as the information processing unit was proposed [12] and the effectiveness of using the qubit neuron-based quantum neural networks was demonstrated [13], [14], [15]; however, the characteristics of applying a quantum neural network to control nonlinear systems have not yet been clarified.…”

Section: Introductionmentioning

confidence: 99%

Remarks on motion control of nonholonomic system (falling cat) by using a quantum neural controller

Takahashi

2012

2012 12th International Conference on Intelligent Systems Design and Applications (ISDA)

Self Cite

View full text Add to dashboard Cite

This paper investigates the application of quantum neural networks to control nonholonomic systems. In this study, the falling cat is treated as an example of a control object. The cat is modelled as two similar cylindrical rigid bodies that represent the front and rear half of its body and the motion of the falling cat is formulated by considering the law of conservation of angular momentum. Because of nonholonomic constraints, the motion control of the falling cat can be treated as a symmetrically affine system without a drift term. A quantum neural controller in which the quantum neural network uses qubit neurons as the information processing unit is designed to solve the control problem that brings the nonholonomic system from the initial to desired position. The computational experiments indicate the feasibility and characteristics of the quantum neural controller in dealing with a nonholonomic system.

show abstract

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

Cited by 5 publications

References 16 publications

Remarks on Servo Controller Using Quantum Neural Network with Qubit Neurons

Remarks on Servo Controller Using Quantum Neural Network with Qubit Neurons

Remarks on an Adaptive-type Self-tuning Controller using Quantum Neural Network with Qubit Neurons

Remarks on motion control of nonholonomic system (falling cat) by using a quantum neural controller

Contact Info

Product

Resources

About