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

Deep learning model training method, system and device and storage medium

A technology of deep learning and training methods, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as parameter redundancy and fitting, solve over-fitting problems, improve training performance and accuracy Effect

Pending Publication Date: 2020-06-05
广东宜通联云智能信息有限公司
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, traditional deep learning models usually contain a large number of redundant parameters, which are prone to overfitting problems, and it is difficult to guarantee optimal results during training.
At present, there is still a lack of a good training mechanism in the prior art to solve the above problems

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
  • Deep learning model training method, system and device and storage medium
  • Deep learning model training method, system and device and storage medium
  • Deep learning model training method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary only for explaining the present invention and should not be construed as limiting the present invention. For the step numbers in the following embodiments, it is only set for the convenience of illustration and description, and the order between the steps is not limited in any way. The execution order of each step in the embodiments can be adapted according to the understanding of those skilled in the art sexual adjustment.

[0051] The following describes in detail the training method and system of the deep learning model proposed according to the embodiments of the present invention with reference to the accompanying drawings. First, the tr...

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 training method, system and device of a deep learning model and a storage medium. The method comprises the following steps: acquiring a connection weight of each layer of nodes in a neural network; determining an orthogonality metric value of each filter in a convolutional layer of the neural network based on the connection weight; optimizing the neural network accordingto the orthogonality measurement value of each filter to obtain a sub-neural network; updating the connection weight of the original neural network through a back propagation algorithm based on the sub-neural network; and outputting the neural network when the neural network with the updated connection weight converges. By using the method provided by the invention, the training network can be adjusted according to the orthogonality of the filter in the process of training the model, the overfitting problem of the model is effectively solved, and the training performance and accuracy of the model are improved. The method can be widely applied to the technical field of artificial intelligence.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a training method, system, device and storage medium of a deep learning model. Background technique [0002] Deep learning solves many challenging problems, and its results have been widely used in computer vision, speech recognition, natural language processing and other fields. Technologies such as image recognition, video processing, and speech recognition based on deep learning have great application prospects and demands on end devices of edge computing systems. However, traditional deep learning models usually contain a large number of redundant parameters, which are prone to overfitting problems, and it is difficult to guarantee optimal results during training. At present, there is still a lack of a good training mechanism in the prior art to solve the above problems. Contents of the invention [0003] The purpose of the present invention is to ...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 王永斌张忠平刘廉如丁雷
Owner 广东宜通联云智能信息有限公司
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