Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method and device for achieving model training, and computer storage medium

A model training and machine learning model technology, applied in the field of machine learning, can solve the problems of low model training efficiency, achieve the effect of improving update efficiency, reducing manual intervention, and improving retraining efficiency

Pending Publication Date: 2021-01-05
HUAWEI TECH CO LTD
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] This application provides a method and device for implementing model training, and a computer storage medium, which can solve the problem of low efficiency of current model training

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
  • Method and device for achieving model training, and computer storage medium
  • Method and device for achieving model training, and computer storage medium
  • Method and device for achieving model training, and computer storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] In order to make the purpose, technical solution and advantages of the present application clearer, the implementation manners of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0063] Feature engineering is the process of using expertise in the data field to create features that enable machine learning algorithms to achieve the best performance, that is, the process of converting the original attributes of data into data features through processing. Attributes are the dimensions of the data itself, such as the original pixels of the image. Features are an important characteristic of the data. Usually, the features are obtained by calculating, combining or converting attributes, such as the original pixels of the image after convolution processing. Get the features of the image. Feature engineering mainly includes: feature construction, feature extraction and feature selection. Among them, there is a cl...

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 method and a device for realizing model training, and a computer storage medium, and belongs to the field of machine learning. When the machine learning model is deteriorated, the analysis equipment firstly obtains validity information of a first feature set, the first feature set comprises a plurality of features used for training to obtain the machine learning model, and the validity information comprises a validity score of each feature in the first feature set; the validity score of the feature is negatively correlated with the correlation between the feature andother features in the first feature set; failure features in the first feature set is determined based on the validity information; and finally,a second feature set which does not include the failurefeatures is generated, wherein the second feature set is used for retraining the machine learning model. According to the method, the failure features in the feature set are determined according to the validity scores of the features calculated on the basis of the correlation between the features, sample data does not need to be labeled, the updating efficiency of the feature set is improved, andthe model training efficiency is also improved.

Description

technical field [0001] The present application relates to the field of machine learning, in particular to a method and device for implementing model training, and a computer storage medium. Background technique [0002] Machine learning refers to allowing machines to train machine learning models based on training samples, so that the machine learning models have category prediction capabilities for data other than training samples. In the specific practical tasks of machine learning, it is very important to select a set of representative features to form a feature set to build a machine learning model. When performing feature selection, labeled sample data is usually used to select feature sets that are strongly correlated with categories to train machine learning models. Among them, the label is used to identify the category of the sample data. [0003] After the machine learning model deteriorates, the machine learning model needs to be retrained to ensure the performan...

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
IPC IPC(8): G06N20/00
CPCG06N20/00G06F18/2113G06F18/2193
Inventor 孙旭东张彦芳张亮刘树成王雅莉
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products