Deep neural network model reinforcing method based on distributed brain-like graph

A deep neural network and neural network technology, applied in the field of deep neural network model reinforcement based on distributed brain-like graphs, can solve the problems of lack of universality of graph network representation, disconnection between biology and neuroscience, and achieve the preservation of integrity , Improve the effect of robustness and close connection

Pending Publication Date: 2022-02-15
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing graph network representation lacks universality and is out of touch with biology and neuroscience

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 neural network model reinforcing method based on distributed brain-like graph
  • Deep neural network model reinforcing method based on distributed brain-like graph
  • Deep neural network model reinforcing method based on distributed brain-like graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, and do not limit the protection scope of the present invention.

[0058] refer to Figure 1 ~ Figure 3 , the present invention provides a method for reinforcing a deep neural network model based on a distributed brain-like map, comprising the following steps:

[0059] (1) Construct the target model data set, specifically:

[0060] The target model data set includes n pieces of sample data, the sample data is divided into a type of sample data, and d% of the sample data is extracted from each type of sample data as the training set D of the target model train , take the remaining sample data of each class as the test set D of the targ...

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 neural network model reinforcing method based on a distributed brain-like graph. According to the method, a key path is applied to a distributed brain-like graph to generate a trunk brain-like graph to carry out more effective constraint on a propagation process and node behaviors on the path, for example, a new gradient loss function is constructed to weaken propagation of noise, so that a new robust brain-like graph structure is grown on the trunk brain-like graph guided by the key path by utilizing graph network indexes such as a length of the feature path and participation coefficients and is reconstructed back to a model, the robustness of the model is improved, and the model is reinforced. According to the method provided by the invention, a brain-like graph is used for showing closer contact with a biological neural network, only some key neurons in the neural network are operated, and the integrity of the neural network is greatly reserved.

Description

technical field [0001] The invention relates to the field of distributed machine learning and artificial intelligence security, in particular to a method for reinforcing a deep neural network model based on a distributed brain-like map. Background technique [0002] With the substantial improvement of software performance and hardware computing power in modern society, artificial intelligence is widely used in computer vision, natural language processing, complex network analysis and other fields and has achieved good results. However, Christian et al. proposed that adding a misleading perturbation imperceptible to the original sample image to generate a new sample would cause the model to give a wrong output with high confidence. This newly generated sample is called an adversarial sample, which poses a potential security threat to deep learning systems, such as face recognition systems, automatic verification systems, and automatic driving systems. [0003] In the past 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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 陈晋音陈宇冲贾澄钰郑海斌金海波
Owner ZHEJIANG 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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap