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

Classification method and apparatus, and computer readable storage medium

A classification method and parallel computing technology, applied in the computer field, can solve the problems of large equipment scale and high cost, and achieve the effect of improving the computing speed.

Inactive Publication Date: 2018-11-06
BEIJING WATERTEK INFORMATION TECH
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Internet companies at home and abroad have built various GPU clusters for deep learning research, which can train neural network models on multiple GPU servers, but the scale of equipment is large and the cost is high

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
  • Classification method and apparatus, and computer readable storage medium
  • Classification method and apparatus, and computer readable storage medium
  • Classification method and apparatus, and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0066] In order to make the purpose, technical solution and advantages of the present invention more clear, the embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined arbitrarily with each other.

[0067] Such as figure 1 Shown, according to a kind of classification method of the present invention, comprises the following steps:

[0068] Step 101: Input feature data into a pre-established deep confidence neural network model;

[0069] In this embodiment, before the method, the method further includes: acquiring data collected by the sensor, and performing signal processing on the acquired data to obtain characteristic data.

[0070] Further, the acquired data is subjected to signal processing to obtain characteristic data, including:

[0071] Divide the acquired data...

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

A classification method and apparatus, and a computer readable storage medium are disclosed. The method includes: feature data is input into a pre-established deep belief neural network model; throughmulti-thread parallel Gibbs sampling, the probability of mutual activation between a hidden layer and an explicit layer is calculated in parallel according to the sampling result, and the weight andbias value between neurons are updated in parallel; the updated weight and bias value between neurons are used as initialization training parameters to supervise the deep belief neural network model;and the trained deep belief neural network model is used for classification and recognition. The present application exerts the advantage of algorithm parallelism and improves the operation speed of the system by multithreaded parallel Gibbs sampling and parallel updating of the weight and bias values between the neurons.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a classification method and device, and a computer-readable storage medium. Background technique [0002] With the rapid growth of data in various industries and the continuous development of databases and data analysis technologies, machine learning and data mining technologies for discovering previously unknown rules and connections have been used in market analysis, industrial production, finance, scientific research, and Web information analysis And engineering diagnosis and other fields, and achieved good results. As the main data analysis mode, the classification algorithm is mainly suitable for predicting classification labels or discrete values, which is a supervised learning problem, usually training first (using training data to train the model, generating model parameters) and then classifying (using test data to generate classification results) , commonly u...

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): G06F17/30G06N3/08
CPCG06N3/084
Inventor 凌茵沈毅
Owner BEIJING WATERTEK INFORMATION TECH
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