An Examination of Qubit Neural Network in Controlling an Inverted Pendulum

Authors:
Noriaki Kouda;Nobuyuki Matsui;Haruhiko Nishimura;Ferdinand Peper
Affiliations:
Matsue National College of Technology, Japan;Division of Computer Engineering, Graduate School of Engineering, Himeji Institute of Technology, University of Hyogo, Japan;Graduate School of Applied Informatics, University of Hyogo, Japan;National Institute of Information and Communications Technology, Japan
Venue:
Neural Processing Letters
Year:
2005

Citing 6
Cited 8

Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
On quantum neural computing

Information Sciences—Intelligent Systems: An International Journal
Image Compression by Layered Quantum Neural Networks

Neural Processing Letters
A multilayered feed-forward network based on qubit neuron model

Systems and Computers in Japan
Qubit neural network and its learning efficiency

Neural Computing and Applications
Neural networks for advanced control of robot manipulators

IEEE Transactions on Neural Networks

Model and Training of QNN with Weight

Neural Processing Letters
Time series forecasting with Qubit Neural Networks

ASC '07 Proceedings of The Eleventh IASTED International Conference on Artificial Intelligence and Soft Computing
Quantum probability distribution network

ICIC'07 Proceedings of the intelligent computing 3rd international conference on Advanced intelligent computing theories and applications
A robust automatic phase-adjustment method for financial forecasting

Knowledge-Based Systems
Quantum perceptron network

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Remarks on multi-layer quantum neural network controller trained by real-coded genetic algorithm

IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Quantized Neural Modeling: Hybrid Quantized Architecture in Elman Networks

Neural Processing Letters
Multi-layer quantum neural network controller trained by real-coded genetic algorithm

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Qubit neuron model is a new non-standard computing scheme that has been found by simulations to have efficient processing abilities. In this paper we investigate the usefulness of the model for a non linear kinetic control application of an inverted pendulum on a cart. Simulations show that a neural network based on Qubit neurons would swing up and stabilize the pendulum, yet it also requires a shorter range over which the cart moves as compared to a conventional neural network model.