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

Model training method based on deep learning and related device

A model training and deep learning technology, applied in the computer field, can solve problems such as poor classification performance, time-consuming and cumbersome training process, and affect the accuracy of model training, so as to avoid algorithm application limitations, reduce large intra-class differences, and improve accuracy rate effect

Pending Publication Date: 2019-11-26
TENCENT TECH (SHENZHEN) CO LTD
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in the detection process of multiple individuals, the above methods need to establish independent models one by one, resulting in time-consuming and cumbersome training process, and due to individual differences and signal fluctuations, the classification performance is not good, which in turn affects the model. training accuracy

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
  • Model training method based on deep learning and related device
  • Model training method based on deep learning and related device
  • Model training method based on deep learning and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0069] The embodiment of the present application provides a deep learning-based model training method and related devices, which can be applied to the training process of the motor imagery brain signal classification model, specifically by obtaining the EEG of multiple individuals and determining the corresponding EEG signal samples , the EEG signal sample is used to indicate the corresponding motor imagery action label; determine a plurality of individual label information and establish a corresponding relationship with the motor imagery action label to determine a training data set; based on the training data set The multiple correspondences in the training data set include the correspondence between the EEG signal sample and the motor imagery action label, multiple The corresponding relationship between the label information of the individual and the motor imagery action label or the corresponding relationship between a plurality of individuals; the EEG decoding model is con...

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 model training method based on deep learning and a related device, and the method comprises the steps: building a classification model based on a plurality of individuals, and carrying out the information sharing of motor imagery electroencephalogram signals collected by different individuals; the accuracy of motor imagery classification being further improved by determining the model loss function through the multiple sub-loss functions, the difference of samples being reduced from multiple dimensions, and then the problem that the intra-class difference is large dueto the environment or different mental states in the individual being reduced. In addition, algorithm application limitation caused by individual differentiation is avoided, common information related to different individual motor imagery action tags is extracted, differences among individuals are reduced, and the accuracy of model training is improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a deep learning-based model training method and related devices. Background technique [0002] Deep learning (DL) is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. Specializes in the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, reorganize existing knowledge structures to continuously improve their performance, especially in the Motor imagery-Brain computer interface (Motor imagery-Brain computer interface, The MI-BCI) system has a wide range of application prospects. It can not only help patients with handicapped limbs such as stroke and hemiplegia to perform rehabilitation training, control objects to achieve self-care, but also entertain ordinary people, such as brain-computer augme...

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): G06K9/00
CPCG06F2218/12
Inventor 赵赫雷梦颖郑青青马锴郑冶枫
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