Coupling neural network bounded cluster projection synchronous adjustment control method and system

A technology of coupling neural network and synchronous adjustment control, applied in neural learning method, biological neural network model, neural architecture, etc., can solve the problems of high cost of synchronous control, inability to carry out effective control, etc., and achieve the effect of effective control

Active Publication Date: 2022-05-13
JIANGNAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] For this reason, the technical problem to be solved by the present invention is to overcome the high cost of synchronous control of non-identical coupled neural network control in the prior art and the inability to effectively control

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
  • Coupling neural network bounded cluster projection synchronous adjustment control method and system
  • Coupling neural network bounded cluster projection synchronous adjustment control method and system
  • Coupling neural network bounded cluster projection synchronous adjustment control method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment provides a coupled neural network bounded clustering projection synchronous adjustment control method, including:

[0050] Step 1: Consider the non-identical neural network and divide it into multiple clusters, and set a target neural network for each sub-category. At this time, the target neural network can be regarded as the leader, while other neural networks can be regarded as its follower By. Firstly, the following coupled neural network model with nonlinear, non-constant and mixed time-varying delays is established:

[0051]

[0052] in: i=1, 2,..., N is the state vector of the node; assuming that N neural networks can be divided into l clusters, and there is N≥l>0, if the i-th neural network and the j-th neural network are in In the zth cluster, define μ i =μ j = z, otherwise there is μ i ≠μ j ; is the μth i The connection weight matrix of the neural network in a cluster; i=1, 2,..., N is the external input vector of the neuron; f ...

Embodiment 2

[0126] In this embodiment, in order to verify the correctness of the method in the above embodiment 1, a network model is built for simulation verification. Neural network is a network mathematical model that constructs a structure similar to the connection of neurons in the brain for information processing. The nonlinear mapping ability of neural network can be used to process data. At the same time, power electronic devices can be used to realize it. For example, in the memristive neural network, transistors, resistors and capacitors are used to form a closed loop to simulate neuron circuits, and non-linear devices such as memristors and memcapacitors are used to simulate the synapses of neural networks. To connect, the specific steps are as follows:

[0127] Step 1: Determine the coupled neural network model as follows:

[0128]

[0129] in:

[0130]

[0131]

[0132] ω 1 = ω 2 = ω 3 = 1, σ 1 = σ 2 =0.4,

[0133] Choose the activation function as f 1 (u)...

Embodiment 3

[0146] Based on the same inventive concept, this embodiment provides a coupled neural network bounded clustering projection synchronous adjustment control system. The problem-solving principle is similar to the coupled neural network bounded clustering projection synchronous adjustment control method, and will not be repeated here.

[0147] The control system includes: a building block for establishing a coupled neural network with multiple clusters of nonlinear, non-constant and mixed time-varying time-delays, and setting a target neural network for each cluster; a setting module for An error coupling neural network is established according to the coupling neural network and the target neural network; a clustering synchronization module is used to design a pinning pulse feedback controller according to the error coupling neural network model, and select a corresponding function based on the pinning pulse feedback controller , to realize the bounded cluster projection synchroni...

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 relates to a synchronous adjustment control method and system for bounded clustering projection of a coupled neural network. The present invention includes establishing a coupled neural network with multiple clusters of nonlinear, non-constant and mixed time-varying time-delays, setting a target neural network for each cluster; establishing error coupling based on the coupled neural network and the target neural network Neural network; design a pinning pulse feedback controller according to the error coupling neural network model, select a corresponding function based on the pinning pulse feedback controller, to realize the bounded clustering between the neural network and the target neural network in each cluster Projection synchronization: By building a network model and using the network model to perform numerical simulations, verify the effect of bounded clustering projection synchronization between the target neural network and the coupled neural network. The invention has low control cost and high control precision.

Description

technical field [0001] The invention relates to the technical field of synchronous control of complex networks, in particular to a method and system for synchronous regulation and control of coupled neural network bounded clustering projections. Background technique [0002] In recent years, the wide application of complex networks in various fields makes the study of complex networks an interesting topic. The phenomenon of forcing systems in a network to behave consistently by calibrating system parameters or applying external control inputs is called synchronization. At present, the clustering behavior of chaotic systems has been widely used in image processing, secure communication, etc., and synchronization phenomenon has become an indispensable part of complex network research. So far, different types of synchronization phenomena have been discussed, such as bounded synchronization, lagged synchronization, cluster synchronization, phase synchronization, projective sync...

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 Patents(China)
IPC IPC(8): G06N3/06G06N3/063G06N3/04G06N3/08G06K9/62
CPCG06N3/061G06N3/063G06N3/08G06N3/045G06F18/23
Inventor 汤泽蒋晨辉王艳纪志成
Owner JIANGNAN UNIV
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