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

WTA neural network based on memristor array and application thereof

A technology of neural network and memristor, applied in the field of neural network, can solve the problems of high power consumption, unfavorable large-scale use, large size of neural network, etc., and achieve the effect of low power consumption, excellent performance and small size

Inactive Publication Date: 2015-12-16
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 30 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Generally speaking, MOSFETs or CMOS are commonly used to physically implement neurons, and the resulting neural network is large in size and consumes a lot of power, which is not conducive to large-scale use.

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
  • WTA neural network based on memristor array and application thereof
  • WTA neural network based on memristor array and application thereof
  • WTA neural network based on memristor array and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Using 12 memristors, 12 MOS tubes, 4 capacitors, 4 resistors, and 4 DC power supplies, connect them according to the connection method described above, that is, a memristor-based neuron with four neurons is constructed. array of WTA neural networks, Such as figure 2 shown. Analyzing the network, its kinetic equation formula (4) can be obtained, where N=4. Through the mathematical analysis of the kinetic equation, it can be verified that the neural network has WTA characteristics.

Embodiment 2

[0033] Using 56 memristors, 56 MOS tubes, 8 capacitors, 8 resistors, and 8 DC power supplies, connect them according to the connection method described above, that is, a memristor-based neuron with eight neurons is constructed. Array of WTA neural networks. Analyzing the network, its kinetic equation formula (4) can be obtained, where N=8. Through the mathematical analysis of the kinetic equation, it can be verified that the neural network has WTA characteristics.

[0034] Carry out MATLAB emulation to embodiment 1, embodiment 2 respectively at last, emulation result respectively Such as image 3 , Figure 4 shown. It can be seen from the simulation results that only one output is positive, and the other outputs are all negative, showing WTA characteristics.

Embodiment 3

[0036] The WTA neural network classifier based on the memristor array combines the BP neural network with the WTA neural network based on the memristor array, and is connected through a converter in the middle. After the output of the first part of the BP network is isolated and driven by the second part of the converter, it is used as the input of the third part of the WTA neural network. Build classifier in conjunction with above-mentioned embodiment 1, its structure Such as Figure 5 shown.

[0037] In order to verify the effect of the classifier, we apply it to the classification and recognition of skin diseases. We used the data in the Dermatology Database to classify the sub-diseases of the large category of erythemato-scuamous skin diseases. We used 366 sets of data: 72 for lichen planus, 49 for pityriasis rosea, 52 for chronic dermatitis, 112 for psoriasis, and 61 for seborrheic Dermatitis (seborrheicdermatitis), 20 groups are red pityriasis hair (pityriasis rubra...

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 present invention belongs to the technical field of a neural network and relates to a WTA neural network based on a memristor array and application thereof. The WTA neural network and application thereof, namely a classifier model, are achieved by a design of the memristor array, thereby proposing a classification identification method that can be used for classifying a dermatology feature. the WTA model consists of a memristor, a MOSFET, a capacitor, a resistor and a power supply. On this basis, the classifier based on memristor array WTA neural network is exported. The purpose of the WTA neural network based on the memristor array and application thereof is to achieve the WTA neural network and theclassifier thereof by the memristor, and to explore the application of the memristor in the neural network and medical decision thereof. Compared to the conventional WTA neural network, the classifier designed by the memristor array in the present invention has excellent properties, and can be applied to the field of medical disease classification and the like.

Description

technical field [0001] The invention relates to a memristor and a WTA neural network, provides a WTA neural network based on a memristor array, and designs an application based on the network. It belongs to the field of neural network technology. Background technique [0002] An artificial neural network is a computational model that abstracts information from a network of neurons in the human brain. The types of neural networks mainly studied include BP neural network, cellular neural network, recurrent neural network, WTA neural network, etc. Among them, the WTA neural network has been continuously expanded in theoretical research and engineering applications, and has shown good intelligent characteristics in the fields of pattern recognition, image processing, and automatic control. [0003] Artificial neural network is composed of a large number of interconnected neurons. Generally speaking, MOSFET or CMOS are commonly used to physically implement neurons, and the res...

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): G06N3/063
Inventor 于永斌刘兴文胡青青门乐飞杨辰宇李成邓建华张容权蔡竟业
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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