CN107506827A - A kind of fixed neuronotropic design method of more threshold values polygamma functions - Google Patents

Abstract

A kind of technical field of the fixed neuronotropic design method of more threshold values polygamma functions, 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, activation primitive with regard to starting that corresponding threshold values, the corresponding password of output and strength values, convey information to distributor, distributor is according to the password and intensity passed over, select those circuit outputs, those circuits are closed.

Description

A kind of fixed neuronotropic design method of more threshold values polygamma functions

Technical field

A kind of technical field of the fixed neuronotropic design method of more threshold values polygamma functions, is to belong to artificial intelligence, bionics, The technical field of circuit design, major technique are that artificial neuron is inputted by multichannel, when accumulated value is less than minimum threshold values, people Work 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 Multiple threshold values, according to cumulative value, reach that threshold values, just start the activation primitive of that corresponding threshold values, export corresponding password And strength values, distributor is conveyed information to, distributor selects those circuits defeated according to the password and intensity passed over Go out, those circuits are closed.

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 component performance that is formed as of the flexible and strong function such as adaptability, self study is updated, and passes through the mutual of complexity Connection relation is achieved, thus artificial neural network is a kind of connection mechanism model, has many key characters of complication system. Artificial neural network is applied to signal transacting, data compression, pattern-recognition, robot vision, knowledge processing and its application, in advance Survey, evaluation and the combinatorial optimization problem such as decision problem, scheduling, route planning.It can be used for mould in Control System Design Intend controlled device characteristic, search and study control law, realize fuzzy and intelligent control, therefore the design to neuron is very Important, because fairly obvious, the shape of neuron is very more, although the mankind classify it, neuron has on thousands of Ten thousand kinds, therefore different neurons also possesses different functions, the present invention is the design method of one of which neuron, existing Neuron design very simple, be exactly all inputs and multiplied by weight, then added up, subtract threshold values, then Activation primitive is set, 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 is that a kind of neuron therein is designed, due to the design of existing neuron Very simple, exactly all inputs and multiplied by weight are added up, subtract threshold values, 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 neuron design, the present invention just It is the design method of one of similar a variety of neuronal functions, a kind of more threshold values polygamma functions determine neuronotropic design side Method, it is characterized in that：More threshold values polygamma function orientation neurons are by input, artificial neuron, transmission line, distributor, output end Composition, input receive the input of upper level artificial neuron or the input by other equipment, people such as the input of neuron The effect of work neuron is added up after value and multiplied by weight input, if cumulative value is less than minimum threshold values, then Artificial neuron would not be activated, without any reaction, if cumulative value is more than minimum threshold values, then artificial neuron's quilt Activation, multiple threshold values are also set up on this minimum threshold values, when cumulative value is more than some threshold values, just start pair of this threshold values Activation primitive is answered, because the activation primitive of setting is different, therefore after being activated, is exported with respective function password and intensity Information, the effect of transmission line are exactly to transmit information, and information can be passed to the place to compare farther out, as the axle of neuron Prominent, the effect of distributor is to receive the information with password and intensity, this information is transmitted to the output end of corresponding password, certainly this Output end is multiple, and the effect of output end is exactly that the numerical value of various activation primitives output is delivered to next layer of artificial neuron Member, and can be multiplied with weight, wherein artificial neuron is made up of using following design, artificial neuron 3 parts, and 1 is Accumulator, 2 be different threshold values, and 3 be different activation primitives, and the effect of accumulator is input and multiplied by weight last layer After added up, 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 is just activated, and the value at this moment inputted will It is compared with different threshold values, for example the value inputted is less than d more than c, then activation primitive corresponding to c threshold values will be started, Output c threshold values corresponds to the password and intensity of activation primitive, and wherein distributor is received artificial neuron and transmitted using following design The password and intensity to come over, each output of distributor is connected, it will design a code-set activated by those functions, pass The password and the code-set of each output end passed are matched, and are matched and are just activated, intensity corresponding to output, matching It cannot be activated on not.

Brief description of the drawings

Fig. 1 is more threshold values polygamma function neuronal structure schematic diagrams, and i-1.1-2.i-3.i-4.i-5 represents input, this Input is a lot, and it is to represent output end for role of delegate, o-1.o-2.o-3.o-4.o-5 to draw 5 here, and this output end is very More, it is for role of delegate to draw 5 here, and a-1 represents artificial neuron, and a-2 represents the insideAccumulator, a.b.c.d are Different threshold values is represented, a-3 represents different activation primitive collection, according to the value of input, function corresponding to activation, corresponding to output The value of password and intensity, b-1 represent distributor, and b-2 represents transmission line, equivalent to the aixs cylinder of neuron.

Implementation

After some neurons are activated, it is information by axonal transport to end, but end is not to be activated to be delivered to down entirely One layer of neuron, be selectively to pass to next layer of neuron, therefore present invention employs such design method, input End receives the input of upper level artificial neuron or the input by other equipment, artificial neuron such as the input of neuron Effect be to be added up after value and multiplied by weight input, if cumulative value is less than minimum threshold values, then artificial neuron Member would not be activated, without any reaction, if cumulative value is more than minimum threshold values, then and artificial neuron is activated, Multiple threshold values are also set up above this minimum threshold values, when cumulative value is more than some threshold values, just start this threshold values corresponds to activation Function, because the activation primitive of setting is different, therefore after being activated, the information with respective function password and intensity is exported, The effect of transmission line is exactly to transmit information, and information can be passed to the place to compare farther out, as the aixs cylinder of neuron, is divided The effect for sending out device is to receive the information with password and intensity, this information is transmitted to the outlet line of corresponding password, and this is defeated certainly It is multiple to go out end, and the effect of output end is exactly that the numerical value of various activation primitives output is delivered to next layer of artificial neuron, And can be multiplied with weight, the neuron as is networked, and it can individually network or artificial with other functions Neuron networks, and forms an artificial brain, it is possible to reaches the function of imitating human brain, due to the artificial neuron of the present invention Member, it is using the form of more threshold values polygamma functions orientation, therefore more functions can be realized, can be with fewer of the invention Artificial neuron, reach sufficiently complex network function.

Claims (1)

1. a kind of fixed neuronotropic design method of more threshold values polygamma functions, it is characterized in that：More threshold values polygamma functions orient neurons It is made up of input, artificial neuron, transmission line, distributor, output end, input is such as the input of neuron, in reception The input of one-level artificial neuron or the input by other equipment, the effect of artificial neuron are value and multiplied by weight input After added up, if cumulative value is less than minimum threshold values, then artificial neuron would not be activated, without any reaction, If cumulative value is more than minimum threshold values, then artificial neuron is activated, and multiple threshold values are also set up on this minimum threshold values, When cumulative value is more than some threshold values, just start the corresponding activation primitive of this threshold values, because the activation primitive of setting is difference , therefore after being activated, the information with respective function password and intensity is exported, the effect of transmission line is exactly to transmit information, and Information can be passed to the place to compare farther out, as the aixs cylinder of neuron, the effect of distributor is to receive band password and strong The information of degree, this information is transmitted to the output end of corresponding password, this certain output end is multiple, and the effect of output end is exactly handle The information transmission of various activation primitive outputs can be multiplied to next layer of artificial neuron with weight, wherein artificial god It is made up of through member using following design, artificial neuron 3 parts, 1 is accumulator, and 2 be different threshold values, and 3 be different activation Function, the effect of accumulator are added up after input and multiplied by weight last layer, the designs of different threshold values be so, if Fixed 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 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 big It is less than d in c, then activation primitive corresponding to c threshold values will be started, output c threshold values corresponds to the password and intensity of activation primitive, Wherein distributor is received password and intensity that artificial neuron passes over, is connected each of distributor using following design Output, it will design the code-set of a code-set activated by those functions, the password passed over and each output end Matched, match and be just activated, intensity corresponding to output is unmatched and cannot activated.