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

Neural network training method and device, image classification method, equipment and medium

A neural network training and neural network technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as low training rate, poor learning effect, and redundancy of large operating costs, and improve transfer learning. effect, the effect of reducing redundancy

Pending Publication Date: 2020-06-12
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing training method based on local domain adaptation has the defect of poor learning effect, and cannot well represent the difference between the source domain and the target domain. Further, the process of neural network training according to the training method Has a large operating overhead and redundancy, and the training rate is low

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
  • Neural network training method and device, image classification method, equipment and medium
  • Neural network training method and device, image classification method, equipment and medium
  • Neural network training method and device, image classification method, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative labor are within the protection scope of the present disclosure.

[0031] The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity, or importance, but are only used to distinguish different components. Similarly, "including" or "including" and other similar words mean that the elements or items appearing in front of the word cover the elements or items listed after the word and their equivalents, without excluding other elements or items. Similar words such as "co...

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 neural network training method and device, an image classification method and device and a medium. The neural network training method comprises the steps that a source domainand a target domain are acquired, the source domain comprises a plurality of first samples, and the target domain comprises a plurality of second samples; respectively determining category weights ofvarious categories corresponding to the source domain and the target domain, and calculating the maximum mean value difference of soft weights of the source domain and the target domain based on the category weights; calculating a redundancy value for network compression based on the batch normalization layer coefficient of the neural network; and training the neural network based on the soft weight maximum mean difference and the redundant value.

Description

Technical field [0001] The present disclosure relates to the field of machine learning technology, and more specifically, to a neural network training method, device, image classification method, device, and medium. Background technique [0002] As a branch of machine learning, the main goal of transfer learning is to transfer the knowledge and methods acquired by the neural network based on the source domain (or called the source domain) to the target domain (or called the target domain), which is similar to the analogy of the human brain. In general, the amount of data in the target domain is less than the amount of data in the source domain. For computers, the so-called transfer learning is a technology that allows existing model algorithms to be slightly adjusted to be applied to a new field and function. For example, a training method based on local domain adaptation can enable a neural network to implement the transfer learning. However, the existing training method based...

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): G06N3/04G06N3/08G06N20/00
CPCG06N3/082G06N3/084G06N20/00G06N3/045
Inventor 马宇哲姚旭峰李睿宇沈小勇余备
Owner TENCENT TECH (SHENZHEN) 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