A Research on the Application of Quantum Neural Network Optimization

Hengyang Su

Abstract


The characters of fixed working hours table including the large amount of input and uncertainty of number of input parameters, make the encoding method has great influence on design method of traditional BP network combining genetic algorithm. This paper analyzes the features of searching ability of the traditional BP and genetic algorithm, based on which combining the quantum calculation and neutral model to compose quantum neurons. Then the quantum neurons are expanded to quantum neutral network to replace the traditional neutral network. Comparing to the drawbacks of the traditional genetic algorithm, the paper adopts a variation clamping mechanism. The mechanism gradually narrows the genetic operation space by fixing not sensitive single gene locus in the populations, so that the gene loci do not meet the requirements are more likely to participate in crossover and mutation to accelerate the speed up the genetic algorithm optimization and prevent it from falling into local extreme value. Finally, based on fixed table of mechanical standard working hours, compared to a variety of commonly used methods, the improved algorithm has better performance.

 

DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4244


Keywords


quantum neural network; improved genetic algorithm; fixed working hours table

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics