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

Deep convolutional neural network method based on deterministic discarding connection

A convolutional neural network, deterministic technology, applied in the fields of digital image processing, deep learning, and computer vision, can solve the problem of inappropriate selection of zero-setting elements, and achieve a wide range of applications, strong generalization capabilities, and simple process steps. Effect

Inactive Publication Date: 2017-11-24
TIANJIN UNIV
View PDF0 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The problem with dropping connections is that the way it chooses to zero elements is random
Therefore, it is inappropriate to select zero elements by random method

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
  • Deep convolutional neural network method based on deterministic discarding connection
  • Deep convolutional neural network method based on deterministic discarding connection
  • Deep convolutional neural network method based on deterministic discarding connection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] The invention provides a method for improving the generalization ability of a deep convolutional neural network based on deterministic discarding connections. The convolutional neural network system mainly includes two parts: a training part and a testing part. The present invention is mainly proposed for the over-fitting problem of deep convolution neural, so it is only applied in the training stage.

[0036] The difference between the deterministic drop connection proposed by the present invention and the random drop connection lies in the way of selecting the weight subset of the filter and setting the selected weight subset to zero. figure 1 and figure 2 The basic ideas of randomly dropping connections and deterministic dropping connections are explained respectively.

[0037] exist figure 1 and figure 2 , a neuron in the current layer uses n o Indica...

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 deep convolutional neural network method based on deterministic discarding connection. The method comprises the following steps: step one, collecting a training data set and carrying out tag marking on the data; step two, setting a structure of a convolutional neural network; step three, determining a threshold t that needs to be discarded by a convolution filter weight, initializing the convolution filter weight and determining an iteration frequency; step four, carrying out convolution operation to obtain a feature maps of all convolution layers and inputting the feature map of the last convolution layer into a classifier to obtain a data classification result so as to complete forward calculation; step five, carrying out updating and convolution filter weight optimization continuously by using a back propagation algorithm from the last convolution layer to the first convolution layer to reduce a training error; and step six, repeating the steps four and five and carrying out iteration to optimize parameters of the convolutional neural network continuously till meeting of a terminal condition.

Description

technical field [0001] The invention relates to the fields of computer vision, digital image processing and deep learning, in particular to a deep convolutional neural network method based on deterministic discard connections. Background technique [0002] In recent years, Deep Convolutional Neural Network (DCNN) has been widely used in speech recognition, face recognition, image classification, automatic driving and many other fields. [0003] The convolutional neural network is composed of several convolutional layers, and the number of convolutional layers represents the depth of the network. The role of the convolutional layer is to extract features. The convolutional layer is obtained by the convolution operation of the filter (or convolution kernel) and the output of the previous layer. Therefore, the filter weights of convolutional neural networks are very important. On the one hand, in order to minimize the training error, the weights are optimized through continu...

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): G06N3/08G06K9/62
CPCG06N3/084G06F18/214
Inventor 李鸿杨庞彦伟
Owner TIANJIN 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