Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for constructing deep convolution neural network model

A neural network model and convolutional neural network technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve the problem of difficulty in determining the depth of the network and the number of feature maps, weak correlation between data samples and network models, and Excessive reliance on human experience and other issues, to overcome excessive reliance on human experience, to achieve adaptive incremental learning, network training time and good recognition effect

Inactive Publication Date: 2017-07-07
SHANDONG UNIV OF TECH
View PDF0 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] But at present, the traditional convolutional neural network structure in the existing technology has shortcomings such as over-reliance on human experience, difficulty in determining the depth of the network and the number of feature maps, and difficult training, and the correlation between data samples and network models is weak.

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
  • Method for constructing deep convolution neural network model
  • Method for constructing deep convolution neural network model
  • Method for constructing deep convolution neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Figure 1-5 It is the best embodiment of the present invention, below in conjunction with attached Figure 1-5 The present invention will be further described.

[0032] Refer to attached Figure 1-5 : A method for building a deep convolutional neural network model, comprising the following steps,

[0033] 1), the convolutional neural network model is initialized, and the initial network model only sets one branch, which includes the input layer, convolutional layer, pooling layer and fully connected layer, and each layer contains only one feature map; at this time The depth of the network is set to 5 layers, there are two convolutional layers and pooling layers, one fully connected layer, and the convolutional layer and pooling layer are set alternately.

[0034] 2) Taking the convergence speed of the convolutional neural network as the evaluation index, the end-to-end global expansion learning is performed on the network until the average error of the convolutional ne...

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 provides a method for constructing a deep convolution neural network model, belonging to the field of mode recognition and machine learning. The method comprises the steps of (1) initializing a convolution neural network model, (2) carrying out end-to-end global extension learning on a network until the average error of a convolution neural network system reaches a preset expected value, (3) after global extension, using a cross validation sample to evaluate network performance, and carrying out local extension learning on the network if a recognition rate does not reach the expected value, (4) adding a new incremental end-to-end extension learning branch, realizing the incremental expansion learning of a network structure, and finally realizing the model construction of the deep convolution neural network. According to the method, a neural element can be added according to needs according to a condition of participating in training samples, the extension expansion and incremental expansion of the network structure are realized, the relevance between a data sample and the network model is enhanced, and the network structure adaptive incremental learning is realized.

Description

technical field [0001] A method for constructing a deep convolutional neural network model belongs to the field of pattern recognition and machine learning. Background technique [0002] Convolutional neural network is a special deep neural network model. Its particularity is reflected in two aspects. On the one hand, the connection between its neurons is not fully connected. On the other hand, the connection between some neurons in the same layer The weights of the connections between are shared (ie the same). Its non-fully connected and weight-sharing network structure makes it more similar to biological neural networks, reducing the complexity of the network model and reducing the number of weights. The convolutional neural network is a multi-layer perceptron specially designed for recognizing two-dimensional images. It has good fault tolerance, parallel processing ability and self-learning ability, and can handle complex situations such as complex environmental informat...

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): G06N3/04G06N3/08G06N99/00
CPCG06N3/08G06N20/00G06N3/048
Inventor 邹国锋傅桂霞赵新宇林钉屹高明亮尹丽菊李海涛
Owner SHANDONG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products