A gradient recursion neural network method with finite time convergence

A recursive neural network, limited time technology, applied in the field of neural network, to achieve a wide range of applications, avoid extra workload and tedious process, and strong practical effect

Inactive Publication Date: 2016-11-23
JISHOU UNIVERSITY
View PDF1 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to overcome the deficiencies of prior art and method, provide a kind of neural dynamics calculation method that the gradient recursive neural network of finite

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 gradient recursion neural network method with finite time convergence
  • A gradient recursion neural network method with finite time convergence
  • A gradient recursion neural network method with finite time convergence

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment 1

[0021] We consider the matrix inversion problem that arises frequently in engineering and science, mathematically defining the matrix inverse A -1 ∈R n×n The equation is AX(t)=I or X(t)A=I, where I∈R n×n is the identity matrix, X(t)∈R n×n is the unknown matrix to be inverted. figure 2 It shows the error convergence of the previous gradient recurrent neural network to solve the matrix inversion problem without using a specially constructed nonlinear activation function. The convergence time is 3.5 seconds, while image 3 It shows the error convergence of solving the matrix inversion problem of the present invention when the specially constructed nonlinear excitation function is used. The convergence time is 0.7 seconds, which is 5 times faster, and the convergence performance is greatly improved.

[0022] The following is the specific implementation method of the gradient recursive neural network for finite time convergence in the present invention.

[0023] First define a...

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 gradient recursion neural network method with finite time convergence. The method comprises the following steps: 1) determining an engineering problem to be solved and describing the engineering problem in a unified manner with a mathematical equation; 2) difining the mathematical equation in step 1 as a positive energy function for scalar values and obtaining a negative gradient derivative of the mathematical equation; 3) designing a gradient recursive neural network by using the negative gradient derivative in step 2), and the gradient recursive neural network is solved in real time by a solver; and 4) exciting the gradient recursive neural network of step 3) with a specially constructed nonlinear function to obtain a gradient recurrent neural network with finite time convergence. The gradient recursion neural network method is characterized in that through construction and usage of the special nonlinear function, the finite time convergence of the gradient recurrent neural network is realized.

Description

technical field [0001] The present invention relates to the aspect of neural network in the field of artificial intelligence, more specifically, relates to a gradient recursive neural network method with limited time convergence. Background technique [0002] Gradient recurrent neural network, as a new emerging technology, has its own unique advantages, such as parallel processing ability, distributed storage ability, strong fault tolerance and strong self-adaptive ability. Therefore, it has been widely used in signal processing, pattern recognition, optimization combination, knowledge engineering, expert system, robot control and so on. However, in the past, the engineering / mathematical problem solving of the gradient recurrent neural network can only converge to the desired solution of the required problem when the time tends to infinity. The ideal situation is only exponential convergence, which cannot make the gradient recurrent neural network converge to our desired so...

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
IPC IPC(8): G06N3/02
Inventor 肖林廖柏林鲁荣波杨正华
Owner JISHOU UNIVERSITY
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