CN107491810A - A kind of design method of more threshold values feedback artificial neurons - Google Patents
A kind of design method of more threshold values feedback artificial neurons Download PDFInfo
- Publication number
- CN107491810A CN107491810A CN201710869582.0A CN201710869582A CN107491810A CN 107491810 A CN107491810 A CN 107491810A CN 201710869582 A CN201710869582 A CN 201710869582A CN 107491810 A CN107491810 A CN 107491810A
- Authority
- CN
- China
- Prior art keywords
- threshold values
- artificial neuron
- input
- artificial
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
Abstract
A kind of technical field of the design method of more threshold values feedback artificial neurons, 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, artificial neuron is provided with multiple threshold values, according to cumulative value, reach that threshold values, this threshold values is passed to activation primitive simultaneously and selects end-apparatus, selecting end-apparatus can be according to the threshold values passed over, those ports are selected to gate, feed back those ports, activation primitive is according to the threshold values transmitted, pass through activation primitive computing, the result of calculating, next layer of artificial neuron is passed to by selecting end-apparatus or feeds back to input.
Description
Technical field
A kind of technical field of the design method of more threshold values feedback artificial neurons, is to belong to artificial intelligence, bionics, electricity
The technical field of road design, major technique is that artificial neuron is inputted by multichannel, when accumulated value is less than minimum threshold values, manually
Neuron, it will not be activated, when cumulative value exceedes the threshold values of setting, artificial neuron is activated, and artificial neuron is provided with more
Individual threshold values, according to cumulative value, reach that threshold values, this threshold values is passed to activation primitive simultaneously and selects end-apparatus, selects end-apparatus
According to the threshold values passed over those ports can be selected to gate, those ports feedback, activation primitive leads to according to the threshold values transmitted
Activation functional operation is crossed, the result of calculating, next layer of artificial neuron is passed to by selecting end-apparatus or feeds back to input.
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
The design method of more threshold values feedback artificial neurons, it is characterized in that：More threshold values feedback artificial neurons are by input, artificial god
Through member, end-apparatus is selected, output end, feedback line composition, input is such as the input of neuron, reception upper level artificial 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 activation primitive simultaneously and selects end-apparatus, selecting end-apparatus can be according to biography
The threshold values passed, those ports are selected to gate, those ports feedback, activation primitive is according to the threshold values transmitted, by activating letter
Number computing, the result of calculating, the passage opened by selecting end-apparatus, next layer of artificial neuron or anti-is passed to from output port
Input is fed to, wherein artificial neuron is using following design, and it is made up of 3 parts, and 1 is accumulator, and its effect is exactly handle
Input is added up, if reaches threshold values, if it exceeds this cumulative value, is just passed to activation primitive simultaneously and selected by threshold values
End-apparatus, 2 be different threshold values, and the design of different threshold values is such, sets minimum threshold values a, a<b<c<D, when the value of input is small
In a, then artificial neuron would not be activated, if the value of input is more than a, artificial neuron is just activated, at this moment inputted
Value will be compared with different threshold values, for example the value inputted is less than d more than c, then will start c values pass to it is sharp
Function living and end-apparatus is selected, select end-apparatus using following design, according to the threshold values transmitted, those can be selected according to this threshold values by selecting end-apparatus
Ports open, those port shutdowns, and select those ports to be fed back according to the threshold values transmitted.
Brief description of the drawings
Fig. 1 is the structure principle chart of more threshold values feedback artificial neurons, i-1.1-2.i-3.i-4.i-5.i-6.i-7.i-
8.i-9.i-10.i-11.i-12 represents input, and this input is a lot, and it is for role of delegate, o-1.o- to draw 12 here
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, draws here
12 are for role of delegate, and a-1 represents artificial neuron, and a-2 represents the insideAccumulator, it is different that a.b.c.d represents the inside
Threshold values, a-3 represents activation primitive, and b-1, which is represented, selects end-apparatus, and b-2 represents activation primitive and selects the line of end-apparatus, and b-3 represents tired
Add device and select the line of end-apparatus, b-4.b-5.b-6.b-7 represents feedback line.
Implementation
The brain of people has thousands of neuron, and some neurons are fed back by exporting, to adjust neuron oneself, due to this
It is a kind of universal alike, therefore the present invention creates a kind of artificial neuron, more threshold values feedbacks are artificial also according to this alike
Neuron is by input, artificial neuron, selects end-apparatus, and output end, feedback line composition, input is such as the input of neuron
End, the input or the input by other equipment, the effect of artificial neuron for receiving upper level artificial neuron are the values input
Added up with after multiplied by weight, if cumulative value is less than threshold values, then artificial neuron would not be activated, not any
Reaction, if cumulative value is more than threshold values, then artificial neuron is activated, and cumulative value is just passed to activation primitive simultaneously
With select end-apparatus, selecting end-apparatus can select those ports to gate according to the threshold values that passes over, those ports feedback, activation primitive root
According to the threshold values transmitted, by activation primitive computing, the result of calculating, the passage opened by selecting end-apparatus, from output end oral instructions
Pass next layer of artificial neuron or feed back to input, such artificial neuron and the artificial neuron of other functions are joined
Net, form an artificial brain, it is possible to reach the function of imitating human brain, be to adopt due to the artificial neuron of the present invention
The form fed back with more threshold values, therefore more functions can be realized, fewer artificial neuron of the invention can be used, reached
To sufficiently complex network function.
Claims (1)
1. a kind of design method of more threshold values feedback artificial neurons, it is characterized in that：More threshold values feedback artificial neurons are by defeated
Enter end, artificial neuron, select end-apparatus, output end, feedback line composition, input is such as the input of neuron, reception upper one
The input or the input by other equipment of level artificial neuron, after the effect of artificial neuron is value and multiplied by weight input
Added up, if cumulative value is less than threshold values, then artificial neuron would not be activated, without any reaction, if tired
The value added is more than threshold values, then artificial neuron is activated, and cumulative value is just passed to activation primitive simultaneously and selects end-apparatus, is selected
End-apparatus can select those ports to gate according to the threshold values passed over, and those ports feedback, activation primitive is according to the valve transmitted
Value, by activation primitive computing, the result of calculating, the passage opened by selecting end-apparatus, next layer is passed to from output port
Artificial neuron feeds back to input, and wherein artificial neuron is designed using following, and it is made up of 3 parts, and 1 is accumulator,
Its effect is exactly that input is added up, if reaches threshold values, if it exceeds threshold values, just simultaneously transmits this cumulative value
To activation primitive and end-apparatus is selected, 2 be different threshold values, and the design of different threshold values is such, sets minimum threshold values a, a<b<c<
D, when the value of input is less than a, then artificial neuron would not be activated, if the value of input is more than a, artificial neuron just by
Activation, the value at this moment inputted will be compared with different threshold values, for example the value inputted is less than d more than c, then will be started
C values pass to activation primitive and select end-apparatus, select end-apparatus using following design, according to the threshold values transmitted, selecting end-apparatus can be according to this
Threshold values selects those ports opens, those port shutdowns, and selects those ports to be fed back according to the threshold values transmitted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710869582.0A CN107491810A (en) | 2017-09-23 | 2017-09-23 | A kind of design method of more threshold values feedback artificial neurons |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710869582.0A CN107491810A (en) | 2017-09-23 | 2017-09-23 | A kind of design method of more threshold values feedback artificial neurons |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107491810A true CN107491810A (en) | 2017-12-19 |
Family
ID=60653045
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710869582.0A Pending CN107491810A (en) | 2017-09-23 | 2017-09-23 | A kind of design method of more threshold values feedback artificial neurons |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107491810A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1107598A (en) * | 1993-06-14 | 1995-08-30 | 莫托罗拉公司 | Artificial neuron and method of using same |
| US6424961B1 (en) * | 1999-12-06 | 2002-07-23 | AYALA FRANCISCO JOSé | Adaptive neural learning system |
| CN1839397A (en) * | 2003-08-22 | 2006-09-27 | 西麦恩公司 | Neural network for processing arrays of data with existent topology, such as images, and application of the network |
| CN102035609A (en) * | 2010-12-15 | 2011-04-27 | 南京邮电大学 | Signal blind detection method based on a plurality of continuous unity feedback neural networks |
| CN103455843A (en) * | 2013-08-16 | 2013-12-18 | 华中科技大学 | Feedback artificial neural network training method and feedback artificial neural network calculating system |
-
2017
- 2017-09-23 CN CN201710869582.0A patent/CN107491810A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1107598A (en) * | 1993-06-14 | 1995-08-30 | 莫托罗拉公司 | Artificial neuron and method of using same |
| US6424961B1 (en) * | 1999-12-06 | 2002-07-23 | AYALA FRANCISCO JOSé | Adaptive neural learning system |
| CN1839397A (en) * | 2003-08-22 | 2006-09-27 | 西麦恩公司 | Neural network for processing arrays of data with existent topology, such as images, and application of the network |
| CN102035609A (en) * | 2010-12-15 | 2011-04-27 | 南京邮电大学 | Signal blind detection method based on a plurality of continuous unity feedback neural networks |
| CN103455843A (en) * | 2013-08-16 | 2013-12-18 | 华中科技大学 | Feedback artificial neural network training method and feedback artificial neural network calculating system |
Non-Patent Citations (1)
| Title |
|---|
| 韦一，沈继忠: "基于多阈值神经元的D型触发器设计", 《浙江大学学报(理学版)》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107766876B (en) | Driving model training method, driver's recognition methods, device, equipment and medium | |
| CN108171323A (en) | A kind of artificial neural networks device and method | |
| CN104035563B (en) | W-PCA (wavelet transform-principal component analysis) and non-supervision GHSOM (growing hierarchical self-organizing map) based electrocardiographic signal identification method | |
| Quraishi et al. | Image recognition and processing using Artificial Neural Network | |
| CN106227043A (en) | adaptive optimal control method | |
| CN109711449A (en) | A kind of image classification algorithms based on full convolutional network | |
| Guo et al. | Algorithm research on improving activation function of convolutional neural networks | |
| CN107563505A (en) | A kind of design method of external control implantation feedback artificial neuron | |
| CN107491810A (en) | A kind of design method of more threshold values feedback artificial neurons | |
| CN110032987A (en) | A kind of surface electromyogram signal classification method based on CMAC Neural Network model | |
| CN110378476A (en) | Approximate realization method, system and medium for maximum pooling layer of pulse convolution neural network | |
| CN107516130A (en) | A kind of more threshold values polygamma functions select the design method of end output artificial neuron | |
| CN107368841A (en) | A kind of underwater manoeuvre Small object recognition methods based on HHT and artificial neural network | |
| CN107563506A (en) | A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron | |
| CN107590536A (en) | A kind of graded potential formula selects the design method of end feedback artificial neuron | |
| CN107886163A (en) | Single-object problem optimization method and device based on AGN and CNN | |
| CN107578097A (en) | A kind of design method of more threshold values polygamma function feedback artificial neurons | |
| CN107609636A (en) | A kind of polygamma function correspondingly exports the design method of feedback function artificial neuron | |
| CN107480779A (en) | Design method that is a kind of while exporting polymorphic function artificial neuron | |
| CN107633300A (en) | A kind of design method of graded potential formula artificial neuron | |
| CN106682651A (en) | Monitoring method for cable insulation leather damage based on neural network | |
| CN107609640A (en) | A kind of threshold values selects the design method of end graded potential formula artificial neuron | |
| CN107657315A (en) | A kind of graded potential formula selects the design method of end output artificial neuron | |
| CN107480780A (en) | A kind of more threshold values polygamma functions select the design method of output artificial neuron more | |
| CN107480783A (en) | A kind of more threshold values list functions select the design method of end output 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 |