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

Data classification model training method and device

A classification model and model training technology, applied in the computer field, can solve problems such as unreachable, low model recognition rate, and difficult to achieve convergence goals, and achieve the effect of preventing overfitting and ensuring performance and accuracy.

Active Publication Date: 2017-06-27
BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD +1
View PDF6 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If a neural network model is trained with a data set of this structure, it is often difficult to achieve the goal of convergence, or the neural network is very easy to overfit, resulting in a low recognition rate of the model and failing to achieve the expected effect.

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
  • Data classification model training method and device
  • Data classification model training method and device
  • Data classification model training method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The following description of at least one exemplary embodiment is merely illustrative in nature and in no way taken as any limitation of the invention, its application or uses. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0028] The relative arrangements of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0029] At the same time, it should be understood that, for the conveni...

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 data classification model training method and device, and relates to the field of computer technology. First, a universal data set of recognition objects with a small number of classes and a large number of samples in each class is used to allow a classification model to have initial recognition performance. Then, parameters of several layers at the top of the classification model are trained by an actual data set of the recognition objects with a large number of classes, so that the classification model can be adapted to specific recognition scenes and reach a convergence effect. Afterwards, the identification data of the object is used to train the classification model overall, so that the classification model can guarantee the convergence and prevent over-fitting, and thus the performance and accuracy of data classification are ensured.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a data classification model training method and device. Background technique [0002] At present, in the fields of image recognition, speech recognition, and voiceprint recognition, basic classification networks are used to train to obtain features, and then further classification is performed to identify the person or voice content of the input data through classification. [0003] Taking image recognition as an example, the general training method is: input several images, and each image will correspond to the corresponding category label. After the neural network is trained with several input images, the network parameters are optimized by iterative learning of the output error. . When the final model error converges to a smaller interval, the training is complete. With the help of this training method, traditional deep networks can achieve better recognition results on pu...

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): G06K9/62
CPCG06F18/2415G06F18/214
Inventor 刘巍葛彦昊陈宇翁志
Owner BEIJING JINGDONG SHANGKE INFORMATION TECH CO LTD
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com