CN107633300A - A kind of design method of graded potential formula artificial neuron - Google Patents
A kind of design method of graded potential formula artificial neuron Download PDFInfo
- Publication number
- CN107633300A CN107633300A CN201710898602.7A CN201710898602A CN107633300A CN 107633300 A CN107633300 A CN 107633300A CN 201710898602 A CN201710898602 A CN 201710898602A CN 107633300 A CN107633300 A CN 107633300A
- Authority
- CN
- China
- Prior art keywords
- value
- threshold values
- artificial neuron
- cumulative
- activation primitive
- 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
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of technical field of the design method of graded potential formula 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, artificial neuron is provided with multiple threshold values, according to cumulative value, reach that threshold values, this threshold values is just passed to activation primitive collection, activation primitive collection will all activate the activation primitive below this threshold values, activation primitive passes to cumulative connector by respective line, cumulative connector can add up the value for each function for being transmitted through coming, value after cumulative is passed to next layer of artificial neuron from output port.
Description
Technical field
A kind of technical field of the design method of graded potential formula artificial neuron, 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 just passed to activation primitive collection, activation primitive collection will
Activation primitive below this threshold values is all activated, activation primitive passes to cumulative connector by respective line, adds up
Connector can add up the value of each function for being transmitted through coming, and it is manually refreshing that the value after cumulative from output port is passed to next layer
Through member.
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 graded potential formula artificial neuron, it is characterized in that:Graded potential formula artificial neuron is by input, artificial god
Through member, cumulative connector, output end composition, input the defeated of upper level artificial neuron is received such as the input of neuron
Enter or the input by other equipment, the effect of artificial neuron is added up after value and multiplied by weight input, if tired
The value added is less than threshold values, then and artificial neuron would not be activated, without any reaction, if cumulative value is more than threshold values,
So artificial neuron is activated, and artificial neuron is provided with multiple threshold values, according to cumulative value, reaches that threshold values, just this
Individual threshold values passes to activation primitive collection, and activation primitive collection will all activate the activation primitive below this threshold values, activate letter
Several operation results oneself pass to cumulative connector by respective line, and cumulative connector can be each activation for being transmitted through coming
The value of function is added up, and the value after cumulative is passed to next layer of artificial neuron, wherein artificial neuron from output port
Using following design, it is made up of 3 parts, and 1 is accumulator, and its effect is exactly that input is added up, if reach threshold values,
If it exceeds this cumulative value, is just passed to activation primitive collection, the design of threshold values is such, sets minimum threshold values by 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 god
Just it is activated through member, 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
C threshold values will be passed to activation primitive collection, activation primitive collection just activates the activation primitive below c threshold values, passed to cumulative
Connector, such as a correspond to f (x1), and b corresponds to f (x2), and c corresponds to f (x3), and d corresponds to f (x4), thus can f (x1), f (x2),
The value of f (x3) activation primitive output passes to cumulative connector by respective line, and cumulative connector will be f (x1), f
(x2), the value of f (x3) activation primitive output is added up, and passes to next layer of artificial neuron, thus can be according to input
The cumulative different value in end, can carry out classification output in output end.
Brief description of the drawings
Fig. 1 is the structure principle chart of graded potential formula 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 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, a.b.c.d represent difference
Threshold values, a-3 represents activation primitive collection, and f (x1), f (x2), f (x3), f (x4) represent the not coactivation in activation primitive collection
Function, b-1 represent cumulative connector, and b-2.b-3.b-4.b-5 represents the line between activation primitive collection and cumulative connector, often
One function has respective line.
Implementation
The brain of people has thousands of neuron, and the mankind have done many experiments and demonstrated, and is given to some neurons different strong
The stimulation of degree, graded potential will be exported, that is to say, that the stimulation of varying strength is given, the voltage of varying strength will be exported,
Therefore a kind of artificial neuron of the invention, form a hierarchical pattern, graded potential formula artificial neuron be by input,
Artificial neuron, cumulative connector, output end composition, input receive upper level artificial neuron such as the input of neuron
The input or the input by other equipment of member, the effect of artificial neuron are added up after value and multiplied by weight input,
If cumulative value is less than threshold values, then artificial neuron would not be activated, without any reaction, if cumulative value is more than
Threshold values, then artificial neuron is activated, and artificial neuron is provided with multiple threshold values, according to cumulative value, reaches that threshold values, just
This threshold values is passed to activation primitive collection, activation primitive collection will all activate the activation primitive below this threshold values, swash
Function living passes to cumulative connector by respective line, and cumulative connector can be carried out the value for each activation primitive for being transmitted through coming
It is cumulative, the value after cumulative is passed to next layer of artificial neuron, the artificial neuron as and other work(from output port
Artificial neuron's networking of energy, forms an artificial brain, it is possible to reaches the function of imitating human brain, due to the present invention's
Artificial neuron, it is the form using graded potential formula, therefore more functions can be realized, the fewer present invention can be used
Artificial neuron, reach sufficiently complex network function.
Claims (1)
1. a kind of design method of graded potential formula artificial neuron, it is characterized in that:Graded potential formula artificial neuron is by defeated
Enter end, artificial neuron, cumulative connector, output end composition, it is artificial to receive upper level such as the input of neuron for input
The input of neuron or the input by other equipment, the effect of artificial neuron are tired out after value and multiplied by weight input
Add, if cumulative value is less than threshold values, then artificial neuron would not be activated, without any reaction, if cumulative value
More than threshold values, then artificial neuron is activated, and artificial neuron is provided with multiple threshold values, according to cumulative value, reaches that valve
This threshold values, is just passed to activation primitive collection by value, and activation primitive collection will all swash the activation primitive below this threshold values
Living, the operation result of oneself is passed to cumulative connector by activation primitive by respective line, and cumulative connector can be being transmitted through
The value of each activation primitive come is added up, and the value after cumulative is passed to next layer of artificial neuron from output port, wherein
Artificial neuron is using following design, and it is made up of 3 parts, and 1 is accumulator, and its effect is exactly that input is added up, and is
It is no to reach threshold values, if it exceeds threshold values, this cumulative value is just passed to activation primitive collection, the design of threshold values be it is such,
Set 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 input
Value is more than a, and artificial neuron is just activated, and the value at this moment inputted will be compared with different threshold values, such as the value inputted
It is less than d more than c, then c threshold values will be passed to activation primitive collection, activation primitive collection is just the activation primitive below c threshold values
Activation, passes to cumulative connector, such as a corresponds to f (x1), and b corresponds to f (x2), and c corresponds to f (x3), and d corresponds to f (x4), thus
The value of f (x1), f (x2), the output of f (x3) activation primitive can be passed to cumulative connector by respective line, add up connection
Device will add up the value of f (x1), f (x2), the output of f (x3) activation primitive, pass to next layer of artificial neuron, so
The different value that can adds up according to input, can carry out classification output in output end.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710898602.7A CN107633300A (en) | 2017-09-28 | 2017-09-28 | A kind of design method of graded potential formula artificial neuron |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710898602.7A CN107633300A (en) | 2017-09-28 | 2017-09-28 | A kind of design method of graded potential formula artificial neuron |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107633300A true CN107633300A (en) | 2018-01-26 |
Family
ID=61102728
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710898602.7A Pending CN107633300A (en) | 2017-09-28 | 2017-09-28 | A kind of design method of graded potential formula artificial neuron |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107633300A (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
- 2017-09-28 CN CN201710898602.7A patent/CN107633300A/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: "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 |
---|---|---|
KR20160076533A (en) | Methods and apparatus for tagging classes using supervised learning | |
CN106295799A (en) | A kind of implementation method of degree of depth study multilayer neural network | |
CN109522925A (en) | A kind of image-recognizing method, device and storage medium | |
CN106227043A (en) | adaptive optimal control method | |
CN109376921A (en) | Based on hereditary artificial fish school optimization RBF neural short-term load forecasting method | |
CN107563505A (en) | A kind of design method of external control implantation feedback artificial neuron | |
CN107633300A (en) | A kind of design method of graded potential formula artificial neuron | |
CN107516130A (en) | A kind of more threshold values polygamma functions select the design method of end output artificial neuron | |
CN106682651A (en) | Monitoring method for cable insulation leather damage based on neural network | |
CN107480779A (en) | Design method that is a kind of while exporting polymorphic function artificial neuron | |
CN107563506A (en) | A kind of voltage-frequency formula selects the design method that frequency exports artificial neuron | |
CN107657315A (en) | A kind of graded potential formula selects 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 | |
CN107609640A (en) | A kind of threshold values selects the design method of end graded potential formula artificial neuron | |
CN105373829B (en) | A kind of full Connection Neural Network structure | |
CN107609636A (en) | A kind of polygamma function correspondingly exports the design method of feedback function artificial neuron | |
CN107491810A (en) | A kind of design method of more threshold values feedback artificial neurons | |
CN107578096A (en) | A kind of voltage-frequency formula selects the design method of end artificial neuron | |
CN107633299A (en) | A kind of design method of voltage-frequency formula artificial neuron | |
CN107480783A (en) | A kind of more threshold values list functions select the design method of end output artificial neuron | |
CN107578097A (en) | A kind of design method of more threshold values polygamma function feedback artificial neurons | |
CN107451657A (en) | A kind of design method of more threshold values polygamma function neurons | |
CN107563504A (en) | A kind of double design methods for selecting end output artificial neuron of implantable activation primitive | |
CN107563501A (en) | A kind of implantable activation primitive 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 |
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: 20180126 |