An Examination of Qubit Neural Network in Controlling an Inverted Pendulum

Authors: kouda, Noriaki¹; Matsui, Nobuyuki²; Nishimura, Haruhiko³; Peper, Ferdinand⁴

Source: Neural Processing Letters, Volume 22, Number 3, December 2005 , pp. 277-290(14)

Publisher: Springer

Buy & download fulltext article:

Price: $47.00 plus tax (Refund Policy)

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.

Keywords: inverted pendulum; quantum neural network; qubit; swing up controll

Document Type: Research article

DOI: http://dx.doi.org/10.1007/s11063-005-8337-2

Affiliations: 1: Matsue National College of Technology, Japan, Email: kouda@matsue-ct.ac.jp 2: Division of Computer Engineering, Graduate School of Engineering, Himeji Institute of Technology, University of Hyogo, Japan, Email: matsui@eng.u-hyogo.ac.jp 3: Graduate School of Applied Informatics, University of Hyogo, Japan, Email: haru@ai.u-hyogo.ac.jp 4: National Institute of Information and Communications Technology, Japan, Email: peper@nict.go.jp

Publication date: 2005-12-01