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

Small sample learning method and device based on sample pair relationship propagation

A learning method and small sample technology, applied in the field of machine learning, can solve problems such as poor generalization ability, low classification accuracy, and no use of information resources, and achieve the effect of high accuracy and good generalization ability

Pending Publication Date: 2021-03-26
BEIHANG UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, the existing small-sample learning methods generally do not model the relationship between support set-query set sample pairs, do not utilize this potential information resource, and still face the problem of low classification accuracy and Poor generalization to new tasks

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
  • Small sample learning method and device based on sample pair relationship propagation
  • Small sample learning method and device based on sample pair relationship propagation
  • Small sample learning method and device based on sample pair relationship propagation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] The technical content of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0062] At present, deep neural networks have very important applications in many aspects such as image recognition, speech recognition, and natural language processing. However, the deep neural network model usually has millions of parameters, and requires supervised training through a large amount of labeled data in order to obtain a relatively good effect. In practice, it is often difficult to provide enough labeled data for deep neural network models.

[0063] To this end, an embodiment of the present invention provides a small-sample learning method based on sample-to-relational propagation. The idea of ​​this method is to fully mine the potential information contained in the support set-query set sample pairs in each task, and to obtain more discriminative information by modeling and propagating the relationship...

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 small sample learning method and device based on sample pair relationship propagation. According to the method, explicit modeling and propagation are performed on the relationship between the sample pairs of the support set query set, so that a relationship code with better discrimination can be obtained. By introducing the pseudo-relationship nodes, the feature information of the query set sample can be effectively reserved. Moreover, the invention further provides an effective transduction learning strategy, and the relation information between the query set samplescan be better mined, so that a more accurate classification result is obtained. Compared with the prior art, the method has the advantages that potential information contained in the sample pair of the support set query set in each task is better mined, and higher accuracy and better generalization ability are achieved when a brand-new task is processed.

Description

technical field [0001] The invention relates to a small-sample learning method, in particular to a small-sample learning method based on support set-query set sample-to-relationship propagation, and also relates to a corresponding small-sample learning device, which belongs to the technical field of machine learning. Background technique [0002] Data is an important resource in the field of machine learning. How to train a model in the absence of data? Few-shot Learning is one of the effective solutions. Small sample learning refers to the study of how to extract effective concepts from one or several limited samples under the condition of sparse samples (each category may have only one or several limited samples), so that the model can quickly adapt to these new No visible category. [0003] In recent years, people have proposed a variety of small sample learning methods. These methods can be broadly classified into optimization-based few-shot learning methods, generati...

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): G06F16/2458G06K9/62G06N3/04G06N3/08
CPCG06F16/2465G06N3/08G06F2216/03G06N3/045G06F18/214G06F18/24
Inventor 刘祥龙马宇晴白世豪刘卫
Owner BEIHANG 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