Online learning method and device based on data fuzziness and medium

A learning method and fuzzy technology, applied in the field of deep learning, which can solve the typical problems of sparse data, weak generalization ability of learning models, and too much input data.

Pending Publication Date: 2021-09-07
华瑞新智科技(北京)有限公司 +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides an online learning method, device and medium based on data ambiguity, which is used to solve the problem that the existing online learning model based on random weight neural network has too much input data, and the input data is typical The data is relatively sparse, leading to technical problems such as weak generalization ability of the learning model

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
  • Online learning method and device based on data fuzziness and medium
  • Online learning method and device based on data fuzziness and medium
  • Online learning method and device based on data fuzziness and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0025] Traditional deep learning has made breakthroughs in many fields, especially computer vision and natural language processing. However, the training of such models often requires GPU servers with very strong computing power, which is unaffordable for various edge devices in industrial IoT scenarios. In order to alleviate this problem, researcher...

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 online learning method and device based on data fuzziness and a medium, and aims to solve the technical problems that too much input data is input into an online learning model, and typicality data in the input data is relatively sparse. The method comprises the steps that a server completes training of fuzzy classifiers based on training sample data, the number of the fuzzy classifiers is 2N+1, and N is a positive integer; a data stream from the terminal is input into the fuzzy classifier; the ambiguity of each input data is determined in the data stream; according to a preset selection mode and the ambiguity of the input data, input data with typicality in a data stream from the terminal is determined, the input data with the typicality is sent to the terminal, wherein the input data with the typicality is used for enabling the terminal to update an online learning model of the random weight neural network. According to the method, the quantity of the input data input into the online learning model is reduced, and meanwhile, the typicality of the input data is ensured.

Description

technical field [0001] This application relates to the field of deep learning technology, and in particular to an online learning method, device and medium based on data ambiguity. Background technique [0002] In some practical application scenarios, the data for training the learning model must be gradually obtained over time. The traditional batch machine learning model that obtains all training data at one time no longer meets the needs of these practical application scenarios, which makes it possible to continuously Online learning models that update self-learning mechanisms have been widely used. Due to the advantages of fast learning speed and low requirements for hardware computing resources, random weight neural network is gradually applied to online learning models. [0003] However, the online learning model based on random weight neural network cannot effectively handle massive input data, and it is necessary to reduce the amount of massive data first. At this ...

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
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/043G06F18/24G06F18/214
Inventor曹伟朋庄浩张继勇蔡恒张均贺李圣东
Owner华瑞新智科技(北京)有限公司