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

Parallel convolutional neural network method based on computer pattern recognition

A convolutional neural network and computer mode technology, applied in the field of parallel convolutional neural networks, can solve the problems of low classification accuracy, poor classification effect, slow convolutional neural network training speed, etc. Achieve and improve the effect of training speed

Inactive Publication Date: 2018-04-06
BEIJING UNIV OF TECH
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, the research of image classification is facing many problems to be solved. The classification effect is poor in complex environments. The training speed of convolutional neural network with ordinary structure is slow, and the classification accuracy is not high. It is also a challenge.

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
  • Parallel convolutional neural network method based on computer pattern recognition
  • Parallel convolutional neural network method based on computer pattern recognition
  • Parallel convolutional neural network method based on computer pattern recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0020] The image classification dataset selects the cifar-10 small object image classification dataset. Cifar-10 consists of 60,000 32*32 RGB color pictures, with a total of 10 categories. The biggest feature of this dataset is that it migrates recognition and classification tasks to universal objects.

[0021] Step 1: Download the cifar-10 small object dataset and store it in the hard disk for subsequent use;

[0022] Step 2: Classify the labels of the training set and test set in the cifar-10 dataset and convert them into one-hot vectors for better recognition by the neural network;

[0023] Step 3: Build a parallel convolutional network structure;

[0024] Step 4: The activation function in the parallel network structure selects relu (non-linear activation unit), and adds a dropout layer (dropout rate is 0.25) to prevent overfitting;

[...

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 parallel convolutional neural network method based on computer pattern recognition. The parallel convolutional neural network method based on computer pattern recognition comprises the following three stages, namely an image classification data collection stage, a parallel convolutional neural network construction stage and a deep convolutional neural network classification stage. The parallel convolutional neural network disclosed by the invention can serve as an actual application platform of a deep learning algorithm for aiding learning; in the current deep learning field, the neural network training speed is improved; and since few hardware cost resources are used in the method disclosed by the invention, the method is easy to implement. The method is composedof an image dataset and a parallel convolutional neural network. The image dataset is composed of various image classification data downloaded from the internet, and the parallel convolutional neuralnetwork is an improved deep convolutional network.

Description

technical field [0001] The invention belongs to the field of image classification, and the invention relates to a parallel convolutional neural network method based on computer pattern recognition. Background technique [0002] With the development of information technology, high technology has been integrated into life in the form of digitization, which has brought a lot of convenience and also promoted the development of digital life. The identification technology has also undergone tremendous changes, from the traditional password verification method to more emerging technologies such as digital certificates and biometric authentication. Especially biometric technology, because it uses the inherent physiological or behavioral characteristics of the human body as the identification basis for individual verification, overcomes the shortcomings of traditional authentication methods that are easy to be lost, forgotten, and easily counterfeited. extensive attention of researc...

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): G06N3/04
CPCG06N3/045
Inventor 李玉鑑方皓达
Owner BEIJING UNIV OF 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