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

Model training method and device, computer storage medium and equipment

A model training and model technology, applied in the field of machine learning, can solve the problem of poor prediction effect of neural network models, and achieve the effect of improving prediction effect and generalization ability.

Pending Publication Date: 2021-12-07
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in related technologies, the sample data is obtained by random sampling, and different sample data are not treated differently, so the neural network model is easy to overfit and underfit, resulting in the prediction of the trained neural network model Ineffective

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
  • Model training method and device, computer storage medium and equipment
  • Model training method and device, computer storage medium and equipment
  • Model training method and device, computer storage medium and equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The technical solutions in the present application embodiment will be described in conjunction with the drawings in the present application embodiment. It will be appreciated that the specific embodiments described herein are merely for explaining the related application, the application is not defined. It also should be noted that, for convenience of description, the accompanying drawings illustrate only the part related to the application.

[0030] All technical and scientific terms used herein are commonly understood by those skilled in the art, unless otherwise defined. The term as used herein only for purposes of describing the present embodiment of the application, not intended to limit the present application.

[0031] In the following description, references to "some embodiments", which describes a subset of all possible embodiments, it will be appreciated that, "some embodiments" may be all the same subset of possible embodiments or different subsets, and It can be...

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 embodiment of the invention provides a model training method and device, a computer storage medium and equipment. The method comprises the steps of obtaining at least two sample data sets, wherein the difficulty ratios in sample data included in the at least two sample data sets are different; respectively training at least two preset models through the at least two sample data sets to obtain at least two training models; and carrying out model fusion on the at least two training models to obtain a target model. Therefore, by adopting the at least two sample data sets with different difficulty ratios, layered sampling of the sample data is realized, so that the prediction effect of the finally obtained target model can be improved; moreover, the at least two sample data sets are utilized to perform model training, and then the target model is obtained through model fusion, so that the generalization ability of the target model is improved.

Description

Technical field [0001] The present application relates to the field of machine learning technology, particularly to a model training method, apparatus, computer storage media and devices. Background technique [0002] Currently, in the use of machine learning to predict or solve scheduling problems, need to use the sample data for training the neural network model, and then use the trained neural network model to solve practical problems. However, in the related art, the sample data is obtained by random sampling, different sample data will not be treated differently, so the neural network model is easy to over-fitting and less fit, leading to the prediction of the neural network model after training Ineffective. Inventive content [0003] The present application provides a model training method, apparatus, and computer storage media device to obtain samples and the target model by layering model fusion, and to increase prediction accuracy and generalization ability of the targe...

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): G06Q10/04G06Q10/06G06Q30/02G06K9/62G06N20/00
CPCG06Q10/04G06Q10/06393G06Q30/0271G06N20/00G06F18/25G06F18/214
Inventor 张琦孙中伟姬艳鑫潘城城刘永平李静晓黄一珉张新曹雨晨张钧皓张少洋苏凯贤刘鸿儒
Owner BEIJING WODONG TIANJUN INFORMATION 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com