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

A method for improving the number of parameters of deep convolution neural network

A technology of convolutional neural network and network parameters, which is applied in the field of improving the number of parameters of deep convolutional neural networks, and can solve the problems of increased calculation amount and too many parameters.

Inactive Publication Date: 2019-01-25
GUANGDONG UNIV OF TECH
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a method for improving the number of parameters of a deep convolutional neural network, while maintaining the recognition rate, it aims to solve the problem of an increase in the amount of calculation caused by too many existing network parameters

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 for improving the number of parameters of deep convolution neural network
  • A method for improving the number of parameters of deep convolution neural network
  • A method for improving the number of parameters of deep convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0065] An embodiment of the present invention provides a method for improving the number of parameters of a deep convolutional neural network, including the following steps: construction of a deep convolutional neural network, improvement of a deep convolutional neural network, training and testing of a deep convolutional neural network , to optimize network parameters;

[0066] 1. Construction of a deep convolutional neural network: Based on the VGGnet-16 network, a deep convolutional neural network with a 14-layer network is designed by analyzing the network layer by layer, which includes an image input layer and a conv5X5 convolutional layer. , MAX-pool2x2 pooling layer, conv3X3 convolutional layer, conv3X3 convolutional layer, MAX-pool2X2 pooling layer, conv3X3 convolutional layer, conv3X3 convolutional layer, conv3X3 conv...

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 relates to a method for improving the parameter number of a deep-layer convolution neural network, which comprises the following steps: step 1, constructing a deep-layer convolution neural network; 2, improving deep-seated convolution neural network; 3, training and testing the deep-seated convolution neural network; 4, optimizing network parameters. Compared with the prior art, theinvention effectively reduces the complexity of the model through the improvement of the structure of the convolution neural network and the reduction and optimization of the network parameters in themodel, while maintaining the original recognition rate of the model, greatly reducing the training time and reducing the hardware requirement.

Description

technical field [0001] The invention relates to the field of deep learning network model compression, and more specifically, relates to a method for improving the number of parameters of a deep convolutional neural network. Background technique [0002] Convolutional neural network is the application of deep learning in image processing. Compared with other machine learning algorithms such as SVM, convolutional neural network has strong generalization, and can convolve image pixels and extract features, and can also use massive images The data fully trains the network parameters to achieve higher results. However, there are too many network parameters, the amount of calculation is greatly increased, and the hardware requirements are also increased. More data is often required, and the training time often increases exponentially. Contents of the invention [0003] The purpose of the present invention is to provide a method for improving the number of parameters of a deep c...

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): G06N3/04G06N3/08
CPCG06N3/084G06N3/045
Inventor 潘晴陈华裔王峰
Owner GUANGDONG 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