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

A discrete-time dynamic feedback assisted winner-take-all competition method

A dynamic feedback, discrete-time technology, applied to instruments, computing models, artificial life, etc.

Pending Publication Date: 2019-03-29
JIANGXI UNIV OF SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although many mathematical models have been used to explain or generate winner-take-all competition, it is still an open question to find a simple model that describes this nonlinear phenomenon and has a wide range of applications through rigorous analysis of its performance. question

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 discrete-time dynamic feedback assisted winner-take-all competition method
  • A discrete-time dynamic feedback assisted winner-take-all competition method
  • A discrete-time dynamic feedback assisted winner-take-all competition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0033] A discrete-time dynamic feedback assisted winner-take-all competition method, including three steps of step (1), step (2), and step (3), these three steps are executed in sequence, and the flow chart is as follows figure 1 As shown, 1 is step (1): the agents in the multi-agent dynamic system form a matrix-type state space, its initial value is randomly generated, and the input corresponding to each agent is also randomly generated. That is, the multi-agent matrix x 1 and x 2 represent the first and second state matrices of the agent, respectively, and the input matrix u represents the input corresponding to all agents in the state matrix, namely Where i=1,2,...,m; j=1,2,...n represents a proxy matrix of m*n, representing its state value, input It is also an m*n matrix, which is the input matrix corresponding to the proxy matrix, and...

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 discrete-time dynamic feedback assisted winner-take-all competition method. The method comprises the following steps: (1) agents in a multi-agent system (a total of m*n) forma state space matrix, the initial state values of which are generated randomly, and the corresponding input matrix u is generated randomly, and then participate in the operation of the dynamic systemto obtain the first state value of each agent; (2) Based on the operation result of step (1), each agent determines its second state value by algorithm, and continues to participate in the iteration of the dynamic system by taking this state value as the initial state of the previous step. (3) Based on the result of step (2), the value of state 2 of m*n agents is output as the iterative result. With the increase of iterative times, only one agent corresponding to the maximum input remains active, and all other agents are suppressed, i.e., winner Take-All phenomenon is simulated. The inventionhas the characteristics of matrix processing, dynamic feedback, optional p-norm and application in image processing.

Description

technical field [0001] The invention relates to the combination of the winner-take-all phenomenon and the control field, in particular to a discrete-time dynamic feedback assisted winner-take-all competition method. Background technique [0002] Winner-take-all (winner-take-all) refers to the phenomenon that the agents in the group compete with each other for activation, and finally only the agent with the largest input remains active, while the others are suppressed. "Winner takes all" competition simulates many competitive phenomena that exist in nature: such as plant generation competition, cortical competitive decision-making, animal social foraging and mating, and competition between neurons in the visual system, etc., and discovered many applications in engineering. Computational power in a winner-take-all competition is exceptionally strong and can yield some of the useful functionality required for computationally intelligent applications. Due to the importance of ...

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): G06N3/00
CPCG06N3/006
Inventor 巫光福周欢廖列法李帅
Owner JIANGXI UNIV OF SCI & TECH
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