CN107563506A - A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron - Google Patents
A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron Download PDFInfo
- Publication number
- CN107563506A CN107563506A CN201710892050.9A CN201710892050A CN107563506A CN 107563506 A CN107563506 A CN 107563506A CN 201710892050 A CN201710892050 A CN 201710892050A CN 107563506 A CN107563506 A CN 107563506A
- Authority
- CN
- China
- Prior art keywords
- frequency
- voltage
- artificial neuron
- ripple
- neuron
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
A kind of voltage-frequency formula selects the technical field of the design method of frequency output artificial neuron, it is to belong to artificial intelligence, bionics, the technical field of circuit design, major technique is that artificial neuron is inputted by multichannel, when accumulated value is less than minimum threshold values, artificial neuron, it will not be activated, when cumulative value exceedes the threshold values of setting, artificial neuron is activated, cumulative value is passed to voltage-to-frequency converter by accumulator, voltage-to-frequency converter can be according to the value transmitted, export the ripple of respective frequencies, pass to and select frequency device, select frequency device according to be transmitted through come ripple frequency, divided according to the frequency of ripple, the ripple of different frequency sections can select different ports to export, pass to next layer of artificial neuron.
Description
Technical field
A kind of voltage-frequency formula selects the technical field of the design method of frequency output artificial neuron, is to belong to artificial intelligence, bionical
Learn, the technical field of circuit design, major technique is that artificial neuron is inputted by multichannel, when accumulated value is less than minimum threshold values
When, artificial neuron, it will not be activated, when cumulative value exceedes the threshold values of setting, artificial neuron is activated, and accumulator is tired
The value added passes to voltage-to-frequency converter, and voltage-to-frequency converter according to the value transmitted, can export the ripple of respective frequencies, pass to and select frequency
Device, select frequency device according to be transmitted through come ripple frequency, divided according to the frequency of ripple, the ripples of different frequency sections can select different
Port exports, and passes to next layer of artificial neuron.
Background technology
Neuron is the elementary cell for forming brain, and the brain of the mankind is that have thousands of individual neurons according to certain rule
Form, for the mankind in order to simulate human brain, the design to artificial neuron is the most important thing, has artificial neuron to form people
Work network, artificial neural network are a kind of mathematical modulos for the structure progress information processing that application is similar to cerebral nerve cynapse connection
Type.In this model, composition network is coupled to each other between substantial amounts of artificial neuron, i.e. " neutral net ", to reach processing
The purpose of information.A kind of kinetic simulation for the distributed parallel information processing algorithm structure for imitating animal nerve network behavior feature
Type., with multichannel input stimulus are received, the part that " excitement " output is produced when exceeding certain threshold value by weighted sum is dynamic to imitate for it
The working method of thing neuron, and the weight coefficient of the structure being coupled to each other by these neural components and reflection strength of association makes
Its " collective behavior " has the various complicated information processing functions.Particularly it is this macroscopically have robust, it is fault-tolerant, anti-interference,
The formation of the flexible and strong function such as adaptability, self study can not only be updated by component performance, and pass through
Complicated interconnecting relation is achieved, thus artificial neural network is a kind of connection mechanism model, has many of complication system
Key character.Artificial neural network be applied to signal transacting, data compression, pattern-recognition, robot vision, knowledge processing and its
Using prediction, evaluation and the combinatorial optimization problem such as decision problem, scheduling, route planning.It can in Control System Design
For simulating controlled device characteristic, search and study control law, realizing fuzzy and intelligent control, therefore to the design of neuron
Very important, because fairly obvious, the shape of neuron is very more, although the mankind classify it, neuron has
Thousands of kinds, therefore different neurons also possesses different functions, the present invention simply devises a kind of artificial neuron, existing
The design very simple of some neurons is single, is exactly all inputs and multiplied by weight, is then added up, subtract valve
Value, then sets activation primitive, passes to next layer of neuron.
The content of the invention
The brain of people is that many neurons are formed, therefore neuron is the elementary cell of neutral net, fairly obvious, nerve
First enormous amount, just there are the neuron of different shape, structure, physiologic character and function, neuron in the different parts of human body
Shape it is very strange very more, although the mankind classify to it, neuron has millions upon millions of kinds, therefore different nerves
Member also possesses different functions, and the present invention simply devises a kind of artificial neuron, due to existing neuron design very
It is simple single, exactly all inputs and multiplied by weight are added up, threshold values is subtracted, then activation primitive is set, pass to
Next layer of neuron, a network is so formed, and so simple design solves many forefathers of the mankind and can not solved
The problem of, tremendous influence is produced to All Around The World, but a kind of this simply artificial neuron meta structure most simply, in real world
The various shapes of neuron, various functions, therefore will invention various functions artificial neuron design, it is a kind of
Voltage-frequency formula selects the design method that frequency exports artificial neuron, it is characterized in that:It is by inputting that voltage-frequency formula, which selects frequency output artificial neuron,
End, artificial neuron, frequency device, output end composition are selected, input receives upper level artificial neuron such as the input of neuron
Input or the input by other equipment, the effect of artificial neuron be to be added up after value and multiplied by weight input, such as
The cumulative value of fruit is less than threshold values, then artificial neuron would not be activated, without any reaction, if cumulative value is more than valve
Value, then artificial neuron is activated, and cumulative value is just passed to voltage-frequency converter, and voltage-frequency converter will be according to transmitting
The value come, changes by voltage-frequency, exports the ripple of respective frequencies, the ripple of this frequency is passed to and selects frequency device, select frequency device according to biography
The frequency for crossing incoming wave is divided, and the ripple of different frequency sections can select different ports to export, and passes to next layer of artificial neuron
Member, wherein artificial neuron are using following design, and it is made up of 2 parts, and 1 is accumulator, and its effect is exactly that input is carried out
It is cumulative, if to reach threshold values, if it exceeds this cumulative value, is just passed to voltage-frequency converter by threshold values, 2 be voltage-frequency conversion
Device, its effect are to receive the value that accumulator passes over, and are transformed into frequency wave, and voltage is higher, and the frequency of output is bigger, such as
The threshold values of neuron is 1 volt, if cumulative value is 1.2 volts, exports the ripple of 2,000,000 frequencies, if 1.5 volts cumulative of value, then
The ripple with regard to 5,000,000 frequencies is exported, according to increasing for voltage, the frequency of output becomes big, and voltage here and the relation of frequency, are bases
What the device and design of different materials determined, wherein selecting, the use of frequency device is such to be designed, the frequency transmitted according to voltage-frequency converter
Rate, several wave bands can be divided into, this wave band will select port corresponding to design in advance, and the port selected from these be defeated
Go out, such as the frequency that voltage-frequency converter transmits is to be less than 10,000,000 more than 0, the setting of frequency dividing is greater than 0 and belongs to f1 less than 2.5 million
Section, is exported by o-1.o-2, belongs to f2 sections less than 5,000,000 more than or equal to 2.5, exported by o-3.o-4.o-6, be less than more than or equal to 5
7.5 million belong to f3 sections, are exported by o-5.o-7.o-11, belong to f4 sections less than 10,000,000 more than or equal to 7.5, defeated by o-8.o-9.o-12
Go out.
Brief description of the drawings
Fig. 1 is that voltage-frequency formula selects the structure principle chart that frequency exports artificial neuron, i-1.1-2.i-3.i-4.i-5.i-6.i-
7.i-8.i-9.i-10.i-11.i-12 representing input, this input is a lot, and it is for role of delegate, o- to draw 12 here
1.o-2.o-3.o-4.o-5.i-6.i-7.i-8.i-9.i-10.i-11.i-12 represents output end, and this output end is a lot, this
In to draw 12 be for role of delegate, a-1 represents artificial neuron, a-2 represents insideAccumulator, the conversion of a-3 voltage-frequency
Device, b-1 select frequency device, and the f1.f2.f3.f4 of the inside represents different wave band divisions, b-2 represent voltage-frequency converter and select frequency device it
Between line.
Implementation
The brain of people has thousands of neuron, and the mankind have done many experiments and demonstrated, given to some neurons different
Stimulating, just export the ripple of different frequency, the ripple of different frequency can selectively discharge different mediators in some nerve endings,
Therefore a kind of artificial neuron of the invention, by inputting different voltage, will export the ripple of different frequency, voltage-frequency formula is selected
Frequency output artificial neuron is by input, artificial neuron, selects frequency device, and output end forms, and input is as defeated in neuron
Enter end, receive the input of upper level artificial neuron or the input by other equipment, the effect of artificial neuron is input
Added up after value and multiplied by weight, if cumulative value is less than threshold values, then artificial neuron would not be activated, and not appoint
What is reacted, if cumulative value is more than threshold values, then artificial neuron is activated, and cumulative value is just passed to voltage-frequency conversion
Device, voltage-frequency converter will be changed according to the value passed over, the ripple of respective frequencies exported, this frequency by voltage-frequency
Ripple, which passes to, selects frequency device, selects frequency device and is divided according to the frequency for being transmitted through incoming wave, and the ripple of different frequency sections can select different ends
Mouth output, passes to next layer of artificial neuron, and such artificial neuron and the artificial neuron of other functions are networked, structure
Into an artificial brain, it is possible to reach the function of imitating human brain, be to use voltage-frequency due to the artificial neuron of the present invention
Formula selects the form of frequency output, therefore can realize more functions, can use fewer artificial neuron of the invention, reach
Sufficiently complex network function.
Claims (1)
1. a kind of voltage-frequency formula selects the design method that frequency exports artificial neuron, it is characterized in that:Voltage-frequency formula selects frequency output artificial neuron
Member is by input, artificial neuron, selects frequency device, output end composition, and input receives upper level such as the input of neuron
The input of artificial neuron or the input by other equipment, the effect of artificial neuron are that the value and multiplied by weight of input is laggard
Row is cumulative, if cumulative value is less than threshold values, then artificial neuron would not be activated, without any reaction, if cumulative
Value be more than threshold values, then artificial neuron is activated, and cumulative value is just passed to voltage-frequency converter, and voltage-frequency converter will
According to the value passed over, changed by voltage-frequency, export the ripple of respective frequencies, the ripple of this frequency is passed to and selects frequency device, is selected
Frequency device is divided according to the frequency for being transmitted through incoming wave, and the ripple of different frequency sections can select different ports to export, and pass to next
Layer artificial neuron, wherein artificial neuron are using following design, and it is made up of 2 parts, and 1 is accumulator, and its effect is exactly
Input is added up, if reach threshold values, if it exceeds this cumulative value, is just passed to voltage-frequency converter, 2 are by threshold values
Voltage-frequency converter, its effect are to receive the value that accumulator passes over, and are transformed into frequency wave, voltage is higher, the frequency of output
It is bigger, such as the threshold values of neuron is 1 volt, if cumulative value is 1.2 volts, exports the ripple of 2,000,000 frequencies, if cumulative value
1.5 volts, then export the ripple with regard to 5,000,000 frequencies, according to increasing for voltage, the frequency of output becomes big, voltage here and frequency
Relation, it is to be determined according to the device and design of different materials, wherein selecting, the use of frequency device is such to be designed, and is changed according to voltage-frequency
The frequency that device transmits, several wave bands can be divided into, this wave band will select port corresponding to design in advance, selected from these
Port output, such as the frequency that transmits of voltage-frequency converter is to be less than 10,000,000 more than 0, and the setting of frequency dividing is greater than 0 and is less than 2.5 million
Belong to f1 sections, exported by o-1.o-2, belong to f2 sections less than 5,000,000 more than or equal to 2.5, exported by o-3.o-4.o-6, more than or equal to 5
Belong to f3 sections less than 7.5 million, exported by o-5.o-7.o-11, belong to f4 sections less than 10,000,000 more than or equal to 7.5, by o-8.o-9.o-
12 outputs.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710892050.9A CN107563506A (en) | 2017-09-27 | 2017-09-27 | A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710892050.9A CN107563506A (en) | 2017-09-27 | 2017-09-27 | A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107563506A true CN107563506A (en) | 2018-01-09 |
Family
ID=60983451
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710892050.9A Pending CN107563506A (en) | 2017-09-27 | 2017-09-27 | A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107563506A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110855605A (en) * | 2019-09-26 | 2020-02-28 | 山东鲁能软件技术有限公司 | Safety protection method, system, equipment and readable storage medium for terminal equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679265A (en) * | 2013-11-21 | 2014-03-26 | 大连海联自动控制有限公司 | MBUN (multi-characteristic bionic unified neuron) model |
CN106875006A (en) * | 2017-01-25 | 2017-06-20 | 清华大学 | Artificial neuron metamessage is converted to the method and system of spiking neuron information |
-
2017
- 2017-09-27 CN CN201710892050.9A patent/CN107563506A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103679265A (en) * | 2013-11-21 | 2014-03-26 | 大连海联自动控制有限公司 | MBUN (multi-characteristic bionic unified neuron) model |
CN106875006A (en) * | 2017-01-25 | 2017-06-20 | 清华大学 | Artificial neuron metamessage is converted to the method and system of spiking neuron information |
Non-Patent Citations (1)
Title |
---|
陈允平等: "《人工神经网络原理及其应用》", 31 August 2002, 中国电力出版社 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110855605A (en) * | 2019-09-26 | 2020-02-28 | 山东鲁能软件技术有限公司 | Safety protection method, system, equipment and readable storage medium for terminal equipment |
CN110855605B (en) * | 2019-09-26 | 2022-05-13 | 山东鲁能软件技术有限公司 | Safety protection method, system, equipment and readable storage medium for terminal equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108197773A (en) | Methods of electric load forecasting, load forecast device and terminal device | |
CN102622418B (en) | Prediction device and equipment based on BP (Back Propagation) nerve network | |
CN103679265A (en) | MBUN (multi-characteristic bionic unified neuron) model | |
CN112149815A (en) | Population clustering and population routing method for large-scale brain-like computing network | |
CN107563506A (en) | A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron | |
CN105373829B (en) | A kind of full Connection Neural Network structure | |
CN110378476A (en) | Approximate realization method, system and medium for maximum pooling layer of pulse convolution neural network | |
CN107563505A (en) | A kind of design method of external control implantation feedback artificial neuron | |
CN107516130A (en) | A kind of more threshold values polygamma functions select the design method of end output artificial neuron | |
CN107578096A (en) | A kind of voltage-frequency formula selects the design method of end artificial neuron | |
CN107480779A (en) | Design method that is a kind of while exporting polymorphic function artificial neuron | |
CN106682651A (en) | Monitoring method for cable insulation leather damage based on neural network | |
CN107798384A (en) | Can be evolved impulsive neural networks construction method and device | |
CN107633299A (en) | A kind of design method of voltage-frequency formula artificial neuron | |
CN107578097A (en) | A kind of design method of more threshold values polygamma function feedback artificial neurons | |
CN107633300A (en) | A kind of design method of graded potential formula artificial neuron | |
CN107451657A (en) | A kind of design method of more threshold values polygamma function neurons | |
CN107480783A (en) | A kind of more threshold values list functions select the design method of end output artificial neuron | |
CN107590536A (en) | A kind of graded potential formula selects the design method of end feedback artificial neuron | |
CN107563504A (en) | A kind of double design methods for selecting end output artificial neuron of implantable activation primitive | |
CN107657315A (en) | A kind of graded potential formula selects the design method of end output artificial neuron | |
CN107491810A (en) | A kind of design method of more threshold values feedback artificial neurons | |
CN107563499A (en) | A kind of design method of the more threshold values polygamma function artificial neurons of codified | |
CN107480778A (en) | Design method that is a kind of while exporting polymorphic function artificial neuron | |
CN107609640A (en) | A kind of threshold values selects the design method of end graded potential formula artificial neuron |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180109 |