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

Machine learning model training method and system for large-scale machine learning system

A machine learning model and machine learning technology, applied in the field of model training, can solve the problems of low flexibility and applicability, cumbersome training methods, low training efficiency, etc., to solve the cumbersome training methods, reduce the amount of model training data, and improve training. The effect of efficiency

Pending Publication Date: 2021-05-11
NANCHANG UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Through the above analysis, the problems and defects of the existing technology are: the existing learning model training method is cumbersome, time-consuming, low training efficiency, and low flexibility and applicability

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 model training method and system for large-scale machine learning system
  • Machine learning model training method and system for large-scale machine learning system
  • Machine learning model training method and system for large-scale machine learning system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0081] The machine learning model training method for large-scale machine learning systems provided by the embodiments of the present invention is as follows: figure 1 As shown, as a preferred embodiment, such as image 3 As shown, the processing and division of the acquired feature set and the incremental data in the current time period through the data preprocessing module and the data preprocessing program provided by the embodiment of the present invention include:

[0082] S201, using the Jaccard index to calculate the weight of each feature data and incremental data for the acquired feature set and incremental data in the current time period, to form a first weight set;

[0083] S202, comparing the weights of the feature data and incremental data in the first weight set with a preset weight threshold, screening the feature data and incremental data that meet the requirements, and obtaining the first data subset;

[0084] S203, taking the first data subset and using the ...

Embodiment 2

[0091] The machine learning model training method for large-scale machine learning systems provided by the embodiments of the present invention is as follows: figure 1 As shown, as a preferred embodiment, such as Figure 4 As shown, the model testing module provided by the embodiment of the present invention uses a model testing program to test the machine learning model obtained through training, including:

[0092] S301. Receive the test request of the machine learning model to be tested;

[0093] S302. Invoke a model test service according to the test request to test the model to be tested by using a test sample set;

[0094] S303. Output a test result of the machine learning model to be tested.

[0095] The request provided by the embodiment of the present invention carries test information of the model to be tested, and the test information includes a model file, a test data set, and parameters of the model to be tested.

[0096] The model testing service provided by the...

Embodiment 3

[0098] The machine learning model training method for large-scale machine learning systems provided by the embodiments of the present invention is as follows: figure 1 As shown, as a preferred embodiment, such as Figure 5 As shown, the model evaluation module provided by the embodiment of the present invention uses an evaluation program to evaluate the machine learning model obtained through training, and obtain model evaluation values, including:

[0099] S401. Obtain the value range of each parameter of the machine learning model through the model evaluation module;

[0100] S402, within the value range of each parameter, use the evaluation program to determine the initial value of the corresponding parameter;

[0101] S403, the central processing unit controls the evaluation program to adjust each parameter to the initial value, and acquires a model evaluation value from the evaluation program.

[0102] The model evaluation value provided by the embodiment of the present...

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 belongs to the technical field of model training, and discloses a machine learning model training method and system for a large-scale machine learning system. The machine learning model training system for the large-scale machine learning system comprises a data acquisition module, a data preprocessing module, a parameter range determination module, a central control module, a model training module, a model test module, a model evaluation module, a model optimization module, a data storage module and an update display module. The training sample set is processed through the data preprocessing module, the feature subsets of the training sample set are obtained, and the model training data volume is reduced; the machine learning model is trained based on incremental learning, so that the accuracy of model training can be improved; the optimal parameter value is determined in the value range of each parameter through the model evaluation module and the model optimization module, and the model parameters are adjusted, so that the training efficiency of the model in machine learning is improved.

Description

technical field [0001] The invention belongs to the technical field of model training, and in particular relates to a machine learning model training method and system for large-scale machine learning systems. Background technique [0002] At present, with the general popularity of machine learning, various machine learning models are getting more and more attention. For a machine learning model, it is usually necessary to train it based on training data (also called training samples), and then use the trained machine learning model to perform some kind of prediction, such as category prediction. [0003] During the training process of the machine learning model, it is necessary to add or modify samples to the machine learning model. In order to increase the training samples of machine learning, it is necessary to add different features, or through a combination of different features, and input them into the machine learning model one by one, but the existing learning model...

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
CPCG06N20/00
Inventor 王卓
Owner NANCHANG UNIV
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