Image recognition-oriented neural network training method and system

A neural network training and neural network technology, applied in the field of computer software, can solve the problems of personnel and economic losses, poor robustness of network generalization, and large generalization error of neural network.

Pending Publication Date: 2022-04-15
广州市智能软件产业研究院
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Based on the above problems, the generalization error of the current neural network is still large, and the robustness of network generalization is poor. When it is applied to safety-critical fields such as autonomous driving and intelligent medical care, there are greater risks and hidden dangers. It is very likely to cause huge human and economic losses

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
  • Image recognition-oriented neural network training method and system
  • Image recognition-oriented neural network training method and system
  • Image recognition-oriented neural network training method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to facilitate understanding of the present invention, the present invention will be further described with reference to the related drawings.

[0057] Unless otherwise defined, all techniques and scientific terms used herein are the same as those of those skilled in the art of the present invention. The terms used herein are merely intended to describe specific embodiments, and is not intended to limit the invention. The terms "and / or" as used herein include any and all combinations of one or more related items.

[0058] The basic idea of ​​the embodiment of the present invention is as follows:

[0059] The weight correlation is part of the loss function (LossFunction) of neural network model training, and the convergence of neural network model training is optimized to obtain a neural network with low weight correlation, that is, higher generalization capabilities. And robust neural network. It mainly includes the following two points:

[0060] Add the weight co...

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 neural network training method and system for image recognition. The method comprises the following steps: S1, acquiring a training image data set; s2, constructing a neural network model, and setting a loss function as J < theta; x, y) is a preset loss function, and g (w) is a regularization item; s3, inputting training data in a training image data set into the neural network model for forward propagation to obtain an image feature vector; s4, calculating a loss function value, and judging whether the neural network model is converged or not; if yes, training is ended, and if not, the step S5 is executed; s5, according to the loss function calculation gradient, back propagation is carried out on the neural network model, the weight of each layer of the neural network model is updated, and the weight of each layer is updated according to the gradient direction for reducing the loss function value; and S6, progressively increasing the number of iterations, and returning to the step S3. According to the method, the neural network with more optimized structure and stronger robustness generalization can be obtained.

Description

Technical field [0001] The present invention relates to the technical field of computer software, and more particularly to a neural network training method and system for image recognition. Background technique [0002] Depth neural networks have been successful in many applications, but some models can have good generalization ability to extensive application scenarios under limited size data sets. It is still a mystery. In order to solve this problem, we need to better understand the reasons for the generalization of deep learning models, which can also bring a lot of benefits, such as providing safety for safe critical application scenarios (such as automatic driving / financial industry). Guaranteed to design a better depth neural network model, further enhance the impliance of the network. [0003] There are currently two aspects of the research field of neural network generalization: [0004] 1. Existing work Most focuses on improving the accuracy of the neural network in t...

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): G06V10/774G06K9/62G06N3/04G06N3/08
Inventor 张亮张立军
Owner 广州市智能软件产业研究院
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
Try Eureka
PatSnap group products