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

Model training method and apparatus

A model training and model technology, applied in the field of data recognition, can solve problems such as inaccurate training models, achieve the effects of ensuring accuracy, reducing training costs, and reducing the risk of overfitting

Inactive Publication Date: 2017-12-22
BEIJING MOSHANGHUA TECH CO LTD
View PDF4 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of this, the technical problem to be solved in this application is to provide a model training method and device, which solves the technical problem of inaccurate training model and over-fitting risk in the prior art

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 apparatus
  • Model training method and apparatus
  • Model training method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The implementation of the present application will be described in detail below with reference to the accompanying drawings and examples, so as to fully understand and implement the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects.

[0045] The technical solutions of the embodiments of the present application are mainly applied to data recognition, especially image recognition and voice recognition. In order to realize data recognition, a recognition model needs to be trained first, and the extracted data features are input into the recognition model for data recognition.

[0046] In order to reduce the cost of collecting training data and alleviate the overfitting of the recognition model, the inventors have found through research that a fully trained target can be obtained through transfer learning by using a fully trained deep learning model in the source domain and a small amount of tr...

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 application discloses a model training method and apparatus. The method comprises: acquiring a deep learning model of a source domain; acquiring training data of a target domain; adjusting a weight parameter of the deep learning model of the source domain by using the training data of the target domain to obtain a deep learning model of the target domain; with the deep learning model of the target domain, extracting data features of the training data; and training a K nearest neighbor classification model by using the data features to obtain an identification model. Therefore, the model training cost is lowered; the model accuracy is improved; and the over-fitting risk is reduced.

Description

technical field [0001] This application belongs to the technical field of data recognition, in particular, it relates to a general classification framework based on deep learning and K-neighborhood. Background technique [0002] In practical applications, it is usually necessary to recognize data such as images, sounds, and texts, so as to perform corresponding operations according to the recognition results. For example, image recognition is performed on image data to identify the image category and realize image classification; voice recognition is performed on voice data to determine the age and gender of the user. [0003] At present, the recognition of data such as images, sounds, and texts is usually realized by using a recognition model, so the recognition model needs to be trained first. [0004] Taking image recognition as an example, the recognition model is an image classifier. When training an image classifier, it is necessary to obtain sample images, extract th...

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): G06K9/62
CPCG06F18/24147G06F18/214
Inventor 张默
Owner BEIJING MOSHANGHUA 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