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

A Neural Network Associative Memory Method Based on Memristor

A neural network and associative memory technology, applied in the field of artificial intelligence, can solve problems such as the inability of neural network circuit connection rights, associative memory accuracy and reliability limitations, etc., to improve output accuracy, reliability and accuracy, and improve The effect of flexibility

Active Publication Date: 2021-01-05
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to propose a neural network associative memory method based on memristor to solve the problem that the connection weight of the current neural network circuit cannot be optimal solve the problem of limited accuracy and reliability of associative memory

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 Neural Network Associative Memory Method Based on Memristor
  • A Neural Network Associative Memory Method Based on Memristor
  • A Neural Network Associative Memory Method Based on Memristor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0024] In the classic case of associative memory, Pavlov’s dog experiment, the dog will salivate when the dog is fed food; the dog will not salivate if the bell is only played without food; ring the bell while feeding food, after a period of time Finally, the dog will salivate even if it only rings the bell without feeding food. Pavlov's dog experiment showed a complete process of associative memory.

[0025] The complete associative memory process shown in Pavlov's dog experiments can be divided into autoassociative memory and heteroassociative memory. Self-associative memory is defined as the external input letter "L", under any initial condition, the neural network can associate the memory output letter "L". Differ...

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

Aiming at the defects in the accuracy and reliability of the current neural network circuit associative memory based on resistance, the present invention proposes a neural network associative memory method based on memristor to solve the problem that the connection weight of the current neural network circuit cannot reach the optimal solution. Problems with limited precision and reliability of associative memory. The invention solves the defect that the connection weight of the neural network circuit realized based on the resistance cannot be adjusted by means of the characteristic of variable resistance value of the memristor, and has better flexibility; the neural network circuit realized by the memristor can adjust the weight value , which can realize the optimal solution of neural network connection weights, thereby improving the accuracy of neural network associative memory; due to the improvement of neural network output accuracy, the reliability and accuracy of neural network associative memory are improved; due to the memristor It is a nanoscale material, so replacing the resistance in the traditional neural network circuit with memristor will make the neural network circuit more miniaturized.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and more specifically relates to an associative memory method realized based on memristive characteristics and neural network stability, which can be applied to pattern recognition. Background technique [0002] In the past few decades, neural networks have been successfully applied in the fields of image processing, pattern recognition, and optimal control. Among them, associative memory has become one of the hot spots in the field of pattern recognition due to its wide application in classification recognition. It is worth noting that the current hardware implementation of neural network circuits uses resistors to simulate the connection strength of synapses between biological neurons. However, the connection strength of biological synapses is variable, but the resistance value of resistors is fixed. This shows that the connection weight of the current neural network circuit cannot reach ...

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): G06N3/063
CPCG06N3/063
Inventor 王雷敏邬杰
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)
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