Machine learning interpretable method and device and storage medium

A machine learning and storage medium technology, applied in the field of artificial intelligence, can solve problems affecting the fidelity and interpretability of interpretation results, loss of useful information, etc., to achieve improved fidelity and interpretability, less sampling, and reduced sampling consumption. effect when

Pending Publication Date: 2021-03-26
LENOVO (BEIJING) LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, for images, natural language, and structured data, there is often a strong correlation between features. If the feature random sampling method is used, the feature correlation will be ignored, and a large amount of useful information will inevitably be lost, thereby affecting the fidelity of the interpretation results. and explanatory

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
  • Machine learning interpretable method and device and storage medium
  • Machine learning interpretable method and device and storage medium
  • Machine learning interpretable method and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are merely intended to be better understood in the art, and the scope of the invention is not limited in any way. Rather, providing these embodiments is to make the present invention more thoroughly and complete, and can fully communicate the scope of the invention to those skilled in the art.

[0029] The technical solutions of the present invention will be further described in detail below with reference to the accompanying drawings and specific examples.

[0030] figure 1 Showing the implementation process of the mechanical learning interpretation method of the embodiment of the present invention Figure one .

[0031] reference figure 1 The embodiment of the present invention provides a machine learning interpretation method, which includes: operation 101, acquiring samples to be explained; operatio...

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 discloses a machine learning interpretable method and apparatus, and a computer readable storage medium. The method comprises the steps of firstly obtaining a to-be-interpreted sample; sampling the to-be-interpreted sample based on the feature correlation of the to-be-interpreted sample to obtain a sampling set comprising a plurality of sampling values; carrying out model training byutilizing the plurality of sampling values to obtain an interpretable model; and finally, explaining the to-be-explained sample by utilizing the explainable model to obtain an explaining result.

Description

Technical field [0001] The present invention relates to the field of artificial intelligence, and more particularly to a machine learning interpretation method, device, and computer readable storage medium. Background technique [0002] The main idea of ​​local interpretable algorithm (LOCAL Interpretable Model-AgnosticExplanations) is the prediction of local approximate target black box models using interpretive models (such as linear models). LIME uses a random sampling mode in the local sampling process, ie, between the features of the signal is independent, and the characteristics are randomly extracted when sampling, which is simple and intuitive. [0003] However, for image, natural language, structured data, there is often a strong correlation between features, and if the characteristic random sampling mode is ignored, it will inevitably lose a lot of useful information, which affects the fidelity of the interpretation result. And interpretation. Inventive content [0004...

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): G06N20/00G06K9/62
CPCG06N20/00G06F18/214
Inventor 师圣杜杨洲范伟
Owner LENOVO (BEIJING) LTD
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