Unlock instant, AI-driven research and patent intelligence for your innovation.

A Method of Symbol-Number Mapping on Memristor Array

A mapping method and memristor technology, applied in the direction of instruments, static memory, digital memory information, etc., can solve the problems of reducing versatility, loss of minimum negative value, poor calculation results, etc., to achieve strong versatility and low consumption Effect

Active Publication Date: 2022-03-18
ZHEJIANG LAB
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, in the process of matrix calculation through memristors, for the mapping of neural network weight values, on the one hand, in the prior art, signed numbers and unsigned values ​​are mapped to a positive memristor array and a negative memristor array. On the memristor array, and then calculate the difference to get the final value, but this method will occupy more resources of the memristor, and will also lose a minimum negative value in the numerical expression range
On the other hand, the mapping to the number of symbols is realized by changing the device or adding an analog circuit. This method is more complicated and reduces the versatility

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 Method of Symbol-Number Mapping on Memristor Array
  • A Method of Symbol-Number Mapping on Memristor Array
  • A Method of Symbol-Number Mapping on Memristor Array

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0046]

[0047]

example 2

[0049]

[0050]

example 3

[0052]

[0053]

[0054] Such as Figure 5 As shown, the mapped value W is N=4 bits, the mapping target is a multi-valued 2-bit memristor (m=2), the decimal number is converted into a binary number, and then the target value will be mapped to 3 memristors on, respectively , , . For example, the decimal number 6 maps to is 0, is 1, is 2; decimal number 3, mapped to is 0, is 0, is 3; the decimal number -4, maps to is 1, is 1, is 0; the decimal number -7, maps to is 1, is 0, is 1. In the actual calculation process, The bit value of a symbol flag will only be 0 or 1, which can be regarded as a binary memristor, and the actual value is multiplied by the coefficient , - It can be regarded as an unsigned number, and the actual value is multiplied by the coefficient , . which is .

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 method for mapping signed numbers on a memristor array. The mapping method directly maps signed numbers on the memristor array in the form of complement code, and according to the bit width of different mapped numbers and the memristor Accurate access to mapping schemes. First, you need to confirm whether the current memristor type device is binary or multi-valued. If it is a multi-valued device, you need to confirm the unit accuracy; then, determine the bit width of the mapped symbol number, and convert the symbol number into complement form binary numbers; finally, the symbolic number mapping scheme is derived. The present invention is suitable for neural network calculations, and the method uses less memristor resource consumption for mapping symbol numbers, has strong versatility, and the numerical coverage range is the same as the actual expression range.

Description

technical field [0001] The invention relates to the field of novel intelligent computing, in particular to a symbol number mapping method on a memristor array. Background technique [0002] At present, research on memristors is becoming more and more extensive, involving various fields, such as security, mathematics, and artificial intelligence. In the field of artificial intelligence, memristors are often used as tools and media for neural network computing, and their characteristics of high read / write speed, low power consumption, and high parallelism are fully reflected. Memristor, Memristor (Memristor) is a circuit device that represents the relationship between magnetic flux and charge. Unlike resistors, the resistance value of memristor is determined by the charge flowing through it. By measuring the resistance value of memristor, we can know The amount of charge flowing through it has the effect of memory charge. Moreover, the integration, power consumption, and rea...

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): G11C13/00
CPCG11C13/0069
Inventor 顾子熙时拓张程高高丽丽王志斌李一琪
Owner ZHEJIANG LAB