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

Simulation method for adjustable weight module of cellular neural network

A neural network and simulation method technology, applied in the field of cellular neural network adjustable weight module simulation, can solve the problem of not finding the cellular neural network adjustable weight module simulation method, etc., to improve integration, reduce power consumption, The effect of downsizing

Inactive Publication Date: 2017-08-22
SOUTHEAST UNIV
View PDF1 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the prior art, there is no simulation method for the adjustable weight module of the cellular neural network based on the memristor.

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
  • Simulation method for adjustable weight module of cellular neural network
  • Simulation method for adjustable weight module of cellular neural network
  • Simulation method for adjustable weight module of cellular neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] Mathematical Model of Cellular Neural Network

[0033] The cellular neural network model of cell C(i,j) is:

[0034]

[0035] In the formula, C is the linear capacitance, and the node voltage v xij Indicates the state of the cell C(i,j), the node voltage v uij Indicates the input of cell C(i,j), the node voltage v yij Indicates the output of cell C(i,j), N r (i,j) represents the neighborhood of cell C(i,j), A(i,j; k,l) is the output feedback template of cell C(i,j), representing the output of cell C(k,l) The connection weight with cell C(i,j), B(i,j; k,l) is the input control template of cell C(i,j), which means the input of cell C(k,l) and cell The connection weight between C(i,j), R represents the resistance, and I represents the independent current source.

[0036] Memristor Mathematical Model

[0037] A memristor is a two-port circuit element consisting of memory, which is defined as the derivative of magnetic flux to charge M(t) is the resistance value o...

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 simulation method for an adjustable weight module of a cellular neural network. A memristive synapsis bridge circuit is built mainly on the basis of a memristor to carry out simulation, and the magnitude and the time of the input pulse of the memristive bridge circuit can be regulated to accurately obtain a required cellular neural network weight template. By use of the simulation method, the adjustable weight module of the cellular neural network can be realized.

Description

technical field [0001] The invention relates to the interdisciplinary field of neural networks and memristors, in particular to a simulation method for a cellular neural network adjustable weight module. Background technique [0002] Cellular Neural Network (CNN) is an information processing system proposed by Professor Cai Shaotang in 1988. Much like a neural network, a CNN is a large-scale nonlinear analog circuit that can process signals in real time. The basic structural circuit unit of a cellular neural network is called a cell, including linear and nonlinear circuit elements, usually linear capacitors, linear resistors, linear and nonlinear controlled sources, and independent sources. The structure of a cellular neural network is very similar to a cellular automaton, that is, any cell is only connected to its neighbors. Neighboring cells can directly influence, and cells that are not directly connected may influence each other through the continuous dynamic propagati...

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): G06F17/50G06N3/06
CPCG06F30/20G06F30/30G06N3/061
Inventor 裴文江王双军王开夏亦犁
Owner SOUTHEAST 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