Training method and device of neural network model, storage medium and terminal equipment

A neural network model and training method technology, applied in biological neural network models and other directions, can solve problems such as the inability to effectively remove model parameter vectors, and achieve the effects of compact models, improved operating efficiency, and reduced parameter vectors

Inactive Publication Date: 2018-11-13
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF8 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the shortcomings of the existing methods, the present invention proposes a neural network model training method, device, storage medium and terminal equipment, which are used to solve the problem that the correlation between model parameter vectors cannot be effectively removed in the prior art, and improve model operation efficiency

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
  • Training method and device of neural network model, storage medium and terminal equipment
  • Training method and device of neural network model, storage medium and terminal equipment
  • Training method and device of neural network model, storage medium and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0073] See figure 1 , figure 1 It is a schematic flowchart of the neural network model training method in the first embodiment of the present invention.

[0074] Such as figure 1 As shown, a neural network model training method includes the following steps:

[0075] S11: Obtain a training data set.

[0076] In the specific implementation of the present invention, the training data set is obtained by downloading it on ImageNet. ImageNet is the name of the computer vision system recognition project. It is currently the world’s largest image recognition database. It is a computer scientist from Stanford in the United States that simulates a human recognition system. Established.

[0077] The structure of ImageNet is basically pyramid type: Directory -> Subdirectory -> Picture set; that is, just download a picture set in ImageNet as the training data set, because each picture in ImageNet has corresponding annotation data, which is convenient for subsequent training; when downloading th...

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 training method of a neural network model. The method comprises the steps of: acquiring a training data set; setting an initial loss function of the to-be-trained neural network model, and using a regularization term to update the initial loss function; and inputting the training data set to the to-be-trained neural network model after updating of the initial loss functionto carry out feature learning training until convergence occurs. In the embodiment of the invention, correlation among model parameter vectors is removed, and model running efficiency is improved. The invention also provides a training device of the neural network model, a storage medium and terminal equipment.

Description

Technical field [0001] The present invention relates to the field of artificial intelligence technology, in particular to a neural network model training method, device, storage medium and terminal equipment. Background technique [0002] Neural networks have strong fitting capabilities, and are now widely used in image classification, speech recognition, face recognition and other fields, and have brought revolutionary progress in related fields, but the amount of network parameters is huge and the reasoning time is slow. Factors still limit the development of neural network models. [0003] At present, in the commonly used neural network model training methods, because the parameter vectors in the neural network model have more redundancy and greater correlation, a large number of training samples are required for training and a longer training time, which directly leads to The training efficiency of neural network models is low. Summary of the invention [0004] Aiming at the s...

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): G06N3/02
CPCG06N3/02
Inventor 杨帆
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap