Quantum image-based feature selection method

A feature selection method and quantum image technology, applied in the field of machine learning, can solve problems such as unobservable, feature set evaluation algorithm failure, etc.

Inactive Publication Date: 2021-11-05
武汉辰亚科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On a quantum computer, due to the unobservable and non-copyable nature of the quantum state, the traditional feature set evaluation algorithm is invalid. Therefore, it is necessary to establish an evaluation method for the quantum image feature set for the quantum computing environment, that is, how to calculate the quantum image feature set pair The contribution of quantum machine learning, and then feature selection

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Quantum image-based feature selection method
  • Quantum image-based feature selection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] In order to make the purpose, technical solution and advantages of the present invention clearer, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0033] Please refer to figure 1 , a quantum image-based feature selection method, comprising the following steps:

[0034] S101: Obtain d eigenvalues ​​of the quantum image, and obtain n rows and d columns of quantum data set D; where n is the number of quantum images;

[0035] S102: Combine the d quantum features of the quantum data set D into a set FS={|f 1 >,|f 2 >,...,|f d >}, where each element |f i > is a quantum image feature;

[0036] S103: Select a subset F={|a in the set FS 1 >,|a 2 >,...,|a k >}, each quantum image feature in F|a i >There are many kinds of values, according to different values, the quantum data set D is divided into M sets, D={D 1 ,D 2 ,...,D M}; where each set D i The values ​​on F are the same;

[0037] S104: L...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides a Quantum image-based feature selection method, and the method comprises the following steps: obtaining d feature values of the quantum image, and obtaining an n-row d-column quantum data set D; combining d quantum features of the quantum data set D into a set FS; selecting a subset F in the set FS, and dividing the quantum data set D into M sets; extracting all d one-dimensional feature sets circularly from the set FS, calculating contribution degrees, and reserving the feature set with the maximum contribution degree; extracting all d * (d-1) two-dimensional feature sets circularly from the set FS, calculating contribution degrees, and reserving the feature set with the maximum contribution degree; sequentially and circularly extracting three-dimensional, four-dimensional,... and d-dimensional feature sets, calculating contribution degrees, retaining the feature set with the maximum contribution degree, and circularly comparing to obtain a finally selected feature set. According to the invention, how to calculate the contribution degree of a quantum image feature set to quantum machine learning by using a quantum entropy method is given on a quantum computer, then quantum image feature selection is carried out, and the method plays a promoting role in research of quantum machine learning and popularization of application of the quantum computer.

Description

technical field [0001] The invention relates to the field of machine learning, in particular to a feature selection method based on quantum images. Background technique [0002] Machine learning is to obtain a model by analyzing the attributes or characteristics of sample objects. when classifying images. Images generally have many features, some of which are critical to building a model, and some are useless. Therefore, before machine learning, it is necessary to select image features that are useful for building a model, that is, image feature selection, that is, to select all image feature sets. the best subset of . In order to select the optimal subset, it is necessary to calculate each quantum image feature set, that is, to determine which quantum image feature set is the optimal feature set. On a quantum computer, due to the unobservable and non-copyable nature of the quantum state, the traditional feature set evaluation algorithm is invalid. Therefore, it is necess...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N10/00G06N20/00
CPCG06N10/00G06N20/00G06F18/211G06F18/24
Inventor 余鹏飞路松峰
Owner 武汉辰亚科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap