An examination of qubit neural network in controlling an inverted pendulum

被引：63

作者：

Kouda, N ^{[1
]}

Matsui, N

Nishimura, H

Peper, F

机构：

[1] Matsue Natl Coll Technol, Matsue, Shimane, Japan

[2] Univ Hyogo, Himeji Inst Technol, Grad Sch Engn, Div Comp Engn, Hyogo, Japan

[3] Univ Hyogo, Grad Sch Appl Informat, Hyogo, Japan

来源：

NEURAL PROCESSING LETTERS | 2005年 / 22卷 / 03期

基金：

日本学术振兴会;

关键词：

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

D O I：

10.1007/s11063-005-8337-2

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 [模式识别与智能系统]; 0812 [计算机科学与技术]; 0835 [软件工程]; 1405 [智能科学与技术];

摘要：

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.

引用

页码：277 / 290

页数：14

共 18 条

[1]

RAPID SOLUTION OF PROBLEMS BY QUANTUM COMPUTATION [J].