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

Multi-stable state oscillation circuit based on Hopfield nerve network

A neural network and oscillating circuit technology, applied in the field of multi-stable state oscillating circuits, can solve problems such as undiscovered multi-stable states, and achieve the effects of important biological significance and value, easy implementation, and simple model structure.

Inactive Publication Date: 2018-03-09
CHANGZHOU UNIV
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] So far, no such multi-stable states have been found in Hopfield-based neural networks

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
  • Multi-stable state oscillation circuit based on Hopfield nerve network
  • Multi-stable state oscillation circuit based on Hopfield nerve network
  • Multi-stable state oscillation circuit based on Hopfield nerve network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Mathematical model: a kind of multi-stable state oscillation circuit based on Hopfield neural network of the present embodiment is as figure 1 shown. At first, the present invention is based on a kind of Hopfield neural network model of 3 neurons, and this mathematical model can be expressed as:

[0021]

[0022] in, is the neuron state vector, tanh(x)=[tanh(x 1 ), tanh(x 2 ), tanh(x 3 )] T is a neuron activation nonlinear function, W is a synaptic weight matrix, which can be expressed as

[0023]

[0024] Among them, k is the coupling connection weight of the first neuron to the third neuron.

[0025] The nonlinear system described by equation (1) is symmetric about the origin. Its symmetry can be obtained from (x 1 ,x 2 ,x 3 )→(–x 1 ,–x 2 ,–x 3 ) The invariance of the model after transformation is obtained, which means that if (x 1 ,x 2 ,x 3 ) is a solution of system (1), then (–x 1 ,–x 2 ,–x 3 ) is its other solution.

[0026] make is an ...

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 multi-stable state oscillation circuit based on a Hopfield nerve network; the circuit comprises an operational amplifier, and a resistor and / or capacitor connected with the operational amplifier, thus finishing the adding, subtracting and integration operations of the nerve network; the circuit employs an existing commercial discrete components design, and develops a hardware circuit based on the Hopfield nerve network. The circuit can form multi-attractor coexistence behaviors under different original states, i.e., multi-stable states, thus providing important practical application values in the biology and information engineering fields.

Description

technical field [0001] The present invention relates to a multi-stable state oscillation circuit based on Hopfield neural network, which helps to deeply understand the role of this multi-stable state in brain information processing and cognitive functions, and provides neurodynamic insights for the understanding of brain functions. Explanation. Background technique [0002] Hopfield neural network is an important milestone in the history of neural network development. It has a wide range of applications in combination optimization pattern recognition, associative memory and stereo vision matching. When the neuron activation function adopts a nonlinear function, the Hopfield neural network system belongs to a nonlinear dynamic system. Like the traditional nonlinear dynamic system, it can also generate chaotic attractors and periodic limits within a certain parameter range. Complex nonlinear dynamic behaviors such as rings and stable point attractors illustrate that the Hopfi...

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): G06N3/063G06N3/04H03K3/3568
CPCH03K3/3568G06N3/063G06N3/044
Inventor 徐权胡爱黄钱辉蒋涛宋哲孙梦霞
Owner CHANGZHOU 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