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

A method and system for incremental machine learning based on transparent computing

A machine learning and transparent computing technology, applied in the field of machine learning, to avoid compatibility problems, alleviate system delays, and alleviate IO blocking effects

Active Publication Date: 2021-02-02
CENT SOUTH UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide an incremental machine learning method and system based on transparent computing to avoid compatibility problems caused by multi-client differences and alleviate system delays caused by insufficient computing power. , alleviate the problem of IO blocking caused by the limited storage capacity of a single node, reduce the system delay caused by communication consumption, and improve user experience

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
  • A method and system for incremental machine learning based on transparent computing
  • A method and system for incremental machine learning based on transparent computing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Such as figure 1 As shown, the framework of the system of the present invention is as figure 1 shown. It mainly includes three parts: transparent server, transparent client, and edge node. Training data can be obtained from three parts, but data training can only be performed on transparent servers and edge nodes with strong computing power.

[0029] The network configuration in the transparent server and the transparent client stores the communication information of all edge nodes from the client to the transparent server. Based on the test model on the transparent client, the transparent client can conduct user testing, and users can give user feedback on the test results to revise their correctness. Transparent clients, edge nodes and transparent servers can all collect data. Once the data is collected at the transparent client, it can send the collected data to the edge nodes or transparent servers through the network. The collected data will be stored in the me...

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 an incremental machine learning method and system based on transparent computing, which adopts an incremental machine learning framework based on transparent computing, so that machine learning can be efficiently performed on the premise of low network dependence. Moreover, the present invention splits and processes the training data, greatly reduces the time consumption of machine learning and improves the efficiency of machine learning while ensuring the test accuracy. In addition, the present invention continuously improves the accuracy of machine learning through incremental feedback learning.

Description

technical field [0001] The invention relates to the field of machine learning, in particular to an incremental machine learning method and system based on transparent computing. Background technique [0002] With the popularity of mobile networks and various lightweight clients, the Internet of Things is constantly changing our daily lives. Various IoT applications such as smartphones, wearable devices, and mobile sensors have been widely used in fields such as medical care, smart home, environmental monitoring, and intelligent transportation. Traditionally, lightweight clients only have the ability to collect and display data. However, in many cases, in order to ensure real-time performance, we prefer to make the client have some functional functions, such as facial recognition, object detection, etc., which do not need to transmit data to the server for processing. In addition, in some areas with poor network connections such as tunnels and remote places, we hope that th...

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 Patents(China)
IPC IPC(8): G06F11/36G06N20/00H04L29/06
CPCG06F11/3688G06N20/00H04L67/01
Inventor 梁中鹤郭克华
Owner CENT SOUTH 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