CN107609643A - The design method of end output artificial neuron is selected in a kind of dual control implantation - Google Patents

Abstract

The technical field of the design method of end output artificial neuron is selected in a kind of dual control implantation,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,Neuron is provided with multiple threshold values,According to cumulative value,Reach that threshold values,This value is just transferred to activation primitive storehouse and activation primitive device,Activation primitive storehouse is according to activation primitive storehouse control terminal and the threshold values passed over,Pass through logical operation,Select activation primitive,It is implanted into activation primitive device,Activation primitive is according to the threshold values transmitted,Pass through the activation primitive computing of implantation,The result of calculating is passed to and selects end-apparatus,The code of end control terminal is selected in input simultaneously,Those ports are selected to open,Those port shutdowns,The result of calculating is passed to next layer of artificial neuron by the port of gating.

Description

The design method of end output artificial neuron is selected in a kind of dual control implantation

Technical field

The technical field of the design method of end output artificial neuron is selected in a kind of dual control implantation, is to belong to artificial intelligence, is imitated Raw to 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 neuron is provided with Multiple threshold values, according to cumulative value, reach that threshold values, this value is just transferred to activation primitive storehouse and activation primitive device, swash Function library living by logical operation, selects activation primitive, implantation swashs according to activation primitive storehouse control terminal and the threshold values passed over Function generator living, activation primitive, by the activation primitive computing of implantation, pass to the result of calculating according to the threshold values transmitted End-apparatus is selected, while the code of end control terminal is selected in input, is selected those ports to open, those port shutdowns, the result of calculating is led to The port for crossing gating 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 The design method of end output artificial neuron is selected in dual control implantation, it is characterized in that：Dual control implantation select end output artificial neuron be by Input, artificial neuron, activation primitive storehouse, activation primitive storehouse control terminal, accumulator output control terminal, select end-apparatus, select end-apparatus Control terminal, output end composition, input receive the input of upper level artificial neuron or by other such as the input of neuron The input of equipment, the effect of artificial neuron is 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 god It is activated through member, threshold values while passes to activation primitive device and activation primitive storehouse, the activation primitive inside activation primitive device, be The code and the threshold values of accumulator inputted by activation primitive storehouse control terminal according to the demand of whole network, after logical operation, The activation primitive that selection needs from activation primitive storehouse, is then implanted into activation primitive device, while according to the demand of whole network, from selecting End-apparatus is selected in end-apparatus control terminal input code, setting, selects end-apparatus can according to those port shutdowns of the Code Selection of input, those Port is opened, and the value that activation primitive exports is passed to next layer of artificial neuron by the port of gating, and double control end refers to, Activation primitive storehouse control terminal is the code inputted according to the demand of whole network, and accumulator control terminal is the valve exported by accumulator Value, passes to activation primitive storehouse, and the activation primitive in activation primitive storehouse is selected by logical operation in the two ports, its Middle artificial neuron is made up of using following design, artificial neuron 3 parts, and 1 is accumulator, and 2 different threshold values, 3 activate letters Number devices, the effect of accumulator are added up after input and multiplied by weight last layer, the designs of different 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, thus c threshold values is passed to can simultaneously activation primitive storehouse and activation primitive device, c threshold values and activation letter The control terminal in number storehouses, selects activation primitive, is implanted into activation primitive device, activation primitive device according to c threshold values and the activation primitive selected, Value after output computing, which passes to, selects end-apparatus.

Brief description of the drawings

Fig. 1 is that the structure principle chart that end exports artificial neuron, i-1.1-2.i-3.i-4.i-5.i- are selected in dual control implantation 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 masterpiece to draw 12 here With o-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 very More, it is for role of delegate to draw 12 here, and a-1 represents artificial neuron, and a-2 represents the insideAccumulator, in accumulator A.b.c.d represent different threshold values, a-3 represents activation primitive device, and b-1, which is represented, selects end-apparatus, b-2 represent artificial neuron and The line between end-apparatus is selected, c-1 represents activation primitive storehouse, and r-1, which is represented, selects end-apparatus control terminal, and r-2 represents the control of activation primitive storehouse End, it is accumulator output control terminal that r-3, which is represented, and accumulator passes to threshold values the line in activation primitive storehouse.

Implementation

The brain of people has thousands of neuron, and these neurons are not unalterable, and they are also constantly evolving it In, and same neuron is in different environments, and different output, it is in some cases, only internal and outer Portion's environment works simultaneously, neuron is exported different values according to different situations, and the present invention devises one manually End output artificial neuron is selected in neuron, dual control implantation, is by input, artificial neuron, activation primitive storehouse, activation primitive storehouse Control terminal, accumulator output control terminal, select end-apparatus, select end-apparatus control terminal, output end 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 threshold values is passed to simultaneously activation primitive device and swashed Function library living, the activation primitive inside activation primitive device, is to be inputted by activation primitive storehouse control terminal according to the demand of whole network Code and accumulator threshold values, after logical operation, from activation primitive storehouse selection need activation primitive, then implantation swash Function generator living, while according to the demand of whole network, from end-apparatus control terminal input code is selected, end-apparatus is selected in setting, and selecting end-apparatus can With those port shutdowns of the Code Selection according to input, those ports are opened, the end that the value that activation primitive exports is passed through gating Next layer of artificial neuron is passed in oral instructions, and double control end refers to, activation primitive storehouse control terminal is defeated according to the demand of whole network The code entered, accumulator control terminal are the threshold values exported by accumulator, pass to activation primitive storehouse, the two ports are by patrolling Computing is collected, the activation primitive in activation primitive storehouse is selected, such artificial neuron and the artificial neuron of other functions Networking, form an artificial brain, it is possible to reach the function of imitating human brain, due to the artificial neuron of the present invention, be The form of end output is selected using dual control implantation, therefore more functions can be realized, can be with fewer of the invention artificial Neuron, reach sufficiently complex network function.

Claims (1)

1. the design method of end output artificial neuron is selected in a kind of dual control implantation, it is characterized in that：It is artificial that end output is selected in dual control implantation Neuron is by input, artificial neuron, activation primitive storehouse, activation primitive storehouse control terminal, accumulator output control terminal, selects end Device, end-apparatus control terminal, output end composition are selected, input receives the defeated of upper level artificial neuron 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 threshold values while activation primitive device and activation primitive storehouse is passed to, inside activation primitive device Activation primitive, it is the threshold values of the code and accumulator inputted by activation primitive storehouse control terminal according to the demand of whole network, passes through After logical operation, from the activation primitive of activation primitive storehouse selection needs, activation primitive device is then implanted into, while according to whole network Demand, from end-apparatus control terminal input code is selected, end-apparatus is selected in setting, selects end-apparatus can according to those ends of the Code Selection of input Mouth is closed, and those ports are opened, and the value that activation primitive exports is passed to next layer of artificial neuron by the port of gating, double Control terminal refers to that activation primitive storehouse control terminal is the code inputted according to the demand of whole network, and accumulator control terminal is by tiring out The threshold values for adding device to export, passes to activation primitive storehouse, the two ports are selected in activation primitive storehouse by logical operation Activation primitive, wherein artificial neuron are made up of using following design, artificial neuron 3 parts, and 1 is accumulator, and 2 is different Threshold values, 3 activation primitive devices, the effect of accumulator are added up after input and multiplied by weight last layer, different threshold values Design 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 swashed Living, if the value of input is more than a, artificial neuron is just activated, and 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, thus c threshold values can be passed to activation primitive storehouse and activation primitive device, c simultaneously Threshold values and the control terminal in activation primitive storehouse, activation primitive is selected, be implanted into activation primitive device, activation primitive device is according to c threshold values and choosing The activation primitive gone out, the value after output computing, which passes to, selects end-apparatus.