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

A double-channel adaptive correction network optimizing system based on a feature generalization layer

A network optimization and adaptive technology, applied in the field of machine learning, can solve the problem of low image quality

Inactive Publication Date: 2018-09-14
HANGZHOU DIANZI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This type of method is relatively simple in modeling, the training process is stable and controllable, and the convergence is fast, but the quality of the generated image is slightly lower than the former

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 double-channel adaptive correction network optimizing system based on a feature generalization layer
  • A double-channel adaptive correction network optimizing system based on a feature generalization layer
  • A double-channel adaptive correction network optimizing system based on a feature generalization layer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0071] The network structure of the present invention such as figure 2 shown, mapping It can be composed of a combination of convolutional layer or linear layer and activation layer, mapping Z→P θ (Y|Z) is the same. After obtaining the conditional distribution of the hidden variable, in order to make the sampling process derivable, it is necessary to introduce an auxiliary Gaussian random variable ε, and express the hidden variable Z as the sum of the deterministic item and the noise weighted item, namely

[0072] Z=μ+σε (18)

[0073] At this time, the distribution of the hidden variable Z has not changed, but the hidden variable random nodes in the network have been converted into definite nodes, and the gradient can be backpropagated.

[0074] In formula (18), εP(ε), let P(ε) be a standard normal distribution, and ⊙ represents the...

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 double-channel adaptive correction network optimizing system based on a feature generalization layer. The system comprises a generalization channel, a correction channel, an error calculation unit and an adaptive correction unit. The generalization channel is used for generalizing original features maps and extracting features of weighting-corrected feature maps layer by layer. The correction channel corrects data in the generalization channel according to the error among the feature maps. The error calculation unit calculates the degree of difference of output featuremaps of some feature extraction layer in the generalization channel and the correction channel. The adaptive correction unit weights the feature map output by some feature extraction layer in the correction channel and the feature map output from the corresponding position of the generalization channel. Error of mean square calculated from all feature extraction nodes in the generalization channel and the correction channel is added into a target function as bound terms; through multiple times of iteration in a training process, a generated feature map is closer to original data, so that generalization error is reduced gradually.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to a dual-channel self-adaptive correction network optimization system based on a feature generalization layer. Background technique [0002] In the face of small-scale data sets, it is necessary to generalize existing data, eliminate model overfitting defects as much as possible, and obtain a high-performance deep neural network classification / regression model. Existing data generalization methods are mainly divided into three categories: data generalization methods based on generative adversarial networks, data generalization methods based on geometric transformations, and data generalization methods based on statistical models. [0003] The Generative Adversarial Network consists of a generator and a discriminator. The former generates a sample from a random vector, and the latter identifies the generated sample and the authenticity of the training set sample...

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): G06N3/04G06K9/62
CPCG06N3/045G06F18/29
Inventor 郭春生李睿哲
Owner HANGZHOU DIANZI 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