Unlock instant, AI-driven research and patent intelligence for your innovation.

Original generative adversarial network model-based residual error network method

A network model and residual technology, applied in the field of deep learning neural network, can solve the problems of small feature range and low learning efficiency, and achieve the effect of improving efficiency

Inactive Publication Date: 2018-04-20
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this case, the range of features learned by the generator is small and the learning efficiency is low

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
  • Original generative adversarial network model-based residual error network method
  • Original generative adversarial network model-based residual error network method
  • Original generative adversarial network model-based residual error network method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0027] This embodiment discloses a residual network method based on the original generative confrontation network model, which specifically includes the following steps:

[0028] Step S1. Construct the original generative adversarial network model, and input the image generated by the generator to the discriminator for network training.

[0029] Step S2, constructing a neural network to function as a generator and a discriminator;

[0030] Different convolution kernels are reflected in different matrix values ​​and different numbers of rows and columns.

[0031] Construct multiple convolution kernels. In the process of processing images, different convolution kernels mean that different features of generated images can be learned during network training.

[0032] In the traditional confrontational network model, the gradient of the convolutional neural network is transmitted layer by layer to the deep layer. During the training process, the gradient will gradually become smal...

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 an original generative adversarial network model-based residual error network method, and belongs to the field of a deep learning neural network. The method comprises the following steps of S1, building an original generative adversarial network model; S2, establishing a neural network to serve as a generator and a discriminator; S3, initializing random noises and inputtingthe noises to the generator; S4, performing convolutional operation on an image in the neural network by utilizing a residual error network; and S5, inputting a loss function obtained by residual error network operation to the generator for performing subsequent training. According to the residual error network-based original generative adversarial network model built by the method, a convolutional mode after the discriminator and the generator receive the image is changed, and the discriminator and the generator can perform learning on image characteristics in a larger range, so that the robustness of a whole network training model can be improved.

Description

technical field [0001] The invention relates to the technical field of deep learning neural networks, in particular to a residual network method based on an original generative confrontation network model. Background technique [0002] Generative Adversarial Network (GAN for short) is a deep learning framework proposed by Goodfellow in 2014. It is based on the idea of ​​"game theory" and constructs two models, the generator and the discriminator. The former The image is generated by inputting (0, 1) uniform noise or Gaussian random noise, which discriminates the input image to determine whether it is an image from the dataset or an image produced by the generator. [0003] In the traditional confrontational network model, the discriminator often operates through the original convolution kernel, analyzes the features of the image generated by the generator, and learns a new feature. It often needs to learn an old feature. Only after it is over. In this case, the range of fe...

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): G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06N3/045G06F18/00
Inventor 周智恒李立军
Owner SOUTH CHINA UNIV OF TECH