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

Semi-supervised learning training method and system and computer readable storage medium

A semi-supervised learning and training method technology, applied in computer parts, computing, character and pattern recognition, etc., can solve problems such as difficult convergence, achieve the effect of improving prediction ability, reducing cost, and assisting training

Active Publication Date: 2019-10-01
视睿(杭州)信息科技有限公司
View PDF4 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this kind of method takes a lot of time to simulate and optimize against, and it is often difficult to converge

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
  • Semi-supervised learning training method and system and computer readable storage medium
  • Semi-supervised learning training method and system and computer readable storage medium
  • Semi-supervised learning training method and system and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] In order to be able to understand the above objectives, features and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the application and the features in the embodiments can be combined with each other if there is no conflict.

[0051] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described here. Therefore, the protection scope of the present invention is not limited to the specific details disclosed below. Limitations of the embodiment.

[0052] figure 1 It shows a flowchart of a training method for semi-supervised learning of the present invention.

[0053] Such as figure 1 As shown, the first aspect of the present invention proposes a se...

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 provides a semi-supervised learning training method and system and a computer readable storage medium, and the method comprises the steps: carrying out the clustering of historical annotation samples, and obtaining a clustering center through calculation; receiving new labeled samples and unlabeled samples; calculating a prediction label of the labeled sample according to the model,and obtaining a first loss function by combining the prediction label and an actual label; comparing and analyzing the consistency of the unlabeled samples and historical labeled samples of the clustering center, and calculating to obtain a second loss function; and optimizing parameters of the model by combining the first loss function and the second loss function and adopting a preset semi-supervised learning algorithm. As long as a small number of samples are labeled, the cost of the labeling process is greatly reduced; a small number of labeled samples are used for guiding a large number of unlabeled samples to carry out feature training, the effect of the unlabeled samples is brought into full play, the training of the model can be further assisted, and the prediction capability of the model is improved.

Description

Technical field [0001] The present invention relates to the technical field of deep learning, in particular to a training method, system and computer readable storage medium for semi-supervised learning. Background technique [0002] In recent years, deep learning has shown a blowout development, and comprehensive breakthroughs have been made in technologies in many fields such as images, speech, and text. AI companies with deep learning as their main technology have mushroomed and developed rapidly, and have brought many typical AI application scenarios, such as face detection, image recognition, voice recognition, text recognition, intelligent monitoring, scene recognition, etc. These AI technologies have penetrated into all aspects of people's work and life, such as face unlocking on mobile phones, Alipay’s "face-scanning" payment, beauty effects when taking pictures on mobile phones, and face detection. Behind these successes, in addition to the continuous innovation of hard...

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
CPCG06F18/23G06F18/2155G06F18/24
Inventor 别晓辉徐盼盼别伟成单书畅
Owner 视睿(杭州)信息科技有限公司
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