JP3203675B2 - Learning method of neural network - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a neural network learning method. More specifically, the present invention relates to a method of accumulating input data and teacher data corresponding to the input data while using a neural network, and successively learning the neural network using the accumulated data. In particular, the present invention relates to a method for efficiently storing input data and teacher data and performing efficient learning using the stored data.

[0002]

2. Description of the Related Art A neural network is known as a circuit network that directly realizes a causal relationship that is difficult to theoretically analyze by a learning effect of a coupling coefficient. That is, the neural network learns the coupling coefficient of the neural network in advance so that an optimal output can be obtained for each of a plurality of discrete inputs, and for any input, It is a network that allows a reasonable output to be obtained directly.

[0003]

However, it is difficult to train a neural network so that it can deal with all possible events. Rather, when a new event occurs and an appropriate output cannot be obtained by actually using the learned neural network, learning including the event is usually performed.

However, when learning of a neural network is newly required, learning cannot be performed using only new input data to be learned and teacher data corresponding thereto. This is because the learned items are deleted from the neural network as a result of the new learning. Therefore, when a new neural network is to be learned, it is necessary to perform learning including all input data used in the previous learning and all teacher data corresponding to the input data.

[0005] As a result, it is necessary to save all input data and teacher data used in the past learning, and there is a problem that the capacity of the storage device becomes enormous as the neural network is used for a long time. Further, since input data and teacher data used for learning are enormous, there is a problem that the learning time is long.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and an object of the present invention is to make learning using a fixed amount of teacher data equivalent to learning using a large number of teacher data having an equivalently wide range. It is.

[0007]

According to an aspect of the present invention, a database storing input data and teacher data corresponding thereto is updated, and a neural network is constructed using the updated database. In the learning method, a similarity indicating the degree of similarity of the input data is calculated for all of the sets composed of two input data arbitrarily selected, and the set of the set having the highest similarity is calculated. The two input data are reduced to one input data based on the two input data, and the corresponding two teacher data are reduced to one teacher data based on the two teacher data. The number of degenerations of the generated input data or teacher data is calculated based on the number of past degenerations of the two degenerated data, and the number of degenerations is calculated. The learning of the neural network is characterized in that, at the time of learning the coupling coefficient, the correction amount of the coupling coefficient is changed in accordance with each degeneration number of each teacher data in the correction operation of the coupling coefficient using each teacher data. Is the way.

[0008]

With respect to a set of two input data arbitrarily selected from the input data, a similarity indicating the degree of similarity between the two input data is calculated. In the set having the highest similarity, two input data are reduced to one input data based on the two input data. At the same time, two teacher data corresponding to the two input data are also reduced to one teacher data based on the two teacher data. The number of times of degeneration of input data or teacher data caused by the degeneration is calculated based on the past number of times of degeneration of two pieces of degenerated data. Then, the number of times of degeneration is stored for each input data or each teacher data. At the time of learning the coupling coefficient of the neural network, the convergence speed of the coupling coefficient is changed according to the number of times of degeneration of each teacher data in the correction operation of the coupling coefficient using each teacher data.

[0009]

By controlling the storage capacity of the database as described above, it is possible to make the content that the amount of stored data exceeds a predetermined amount. In addition, since the data stored in the database is reduced to two data having the highest similarity, the database is a set of the most dispersed data if the data storage amount is constant. Therefore, effective learning of the neural network is achieved. Furthermore, teacher data with a large number of degenerations means that teacher data similar to the teacher data has been added to the database as much as possible. In other words, the teacher data having a larger number of times of degeneration is more important teacher data, and it is desirable that the neural network after learning strongly shows the characteristic taught by the teacher data. Therefore,
According to the present invention, when the coupling coefficient is learned from all the teacher data, the learning is performed so that the convergence speed of the coupling coefficient is changed according to the number of degenerations of each teacher data. The learning is executed more effectively than the learning using the teacher data with a small number of degenerations. Therefore, the input / output characteristics of the neural network are
Although the learning is based on a limited number of teacher data, an effective characteristic is obtained that includes all the teacher data generated in past use.

[0010]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS 1. Neural Network As shown in FIG. 1, a neural network 10 of this embodiment has a three-layer structure of an input layer LI, an output layer LO, and an intermediate layer LM. The input layer LI has e input elements, the output layer LO has g output elements, and the intermediate layer LM has f output elements.

A multilayer neural network is generally defined as a device that performs the following operations. Output O ⁱ _j of the j-th element of the i-layer is calculated by the following equation. Here, i ≧ 2.

[0012]

O ⁱ _j = f (I ⁱ _j ) (1)

(Equation 2)

[Equation 3] f (x) = 1 / {1 + exp (-x)} (3)

[0013] However, V ⁱ _j bias of the j th processing element of the i-th layer, W ^i-1 _k, ⁱ _j is the first i-1 layer k-th element and the j of the i-th layer The coupling coefficient between the first element and O ¹ _j represents the output value of the j-th element in the first layer. That is, since it is the first layer, the input is output as it is without performing any operation,
It is also the input value of the j-th element in the input layer (first layer).

Next, a specific calculation procedure of the three-layered neural network 10 shown in FIG. 1 will be described with reference to FIG. In step 100, the intermediate layer (second
The j-th element of the layer) inputs the output value O ¹ _j (input data of the first layer) from each element of the input layer (first layer),
The product-sum operation of the following equation, which is obtained by embodying equation (2) using the layer number and the number of elements in the first layer, is performed.

(Equation 4)

Next, in step 102, the output of each element of the intermediate layer (second layer) is calculated by the following equation using the sigmoid function of the product-sum function value of the input value of equation (4).
The output value of the j-th element in the second layer is calculated by the following equation.

[0016]

O ² _j = f (I ² _j ) = 1 / ｛1 + exp (−I ² _j )｝ (5) The output value O ² _j is the input of each element of the output layer (third layer). Value. Next, in step 104, the output layer (third
The product-sum operation of the input values of each element of the layer is executed.

[0017]

(Equation 6) Next, in step 106, similarly to equation (5),
The output value O ³ _j of each element in the output layer is calculated by the sigmoid function.

[0018]

O ³ _j = f (I ³ _j ) = 1 / {1 + exp (-I ³ _j )} (7)

2. Learning of the Neural Network This neural network is learned by the procedure shown in FIG. 3 as initial learning. The coupling coefficient is performed by a well-known back propagation method. This learning is repeatedly executed for a large number of input data relating to various events so that each output becomes each optimal teacher data.

In step 200 of FIG. 3, a learning signal of each element in the output layer is calculated by the following equation.

Y ³ _j = (T _j −δ _j ) · f ^′ (I ³ _j ) (8) where T _j is teacher data for an arbitrary output δ _j and is externally provided. Also, f ^′ (x) is a derivative of the jigmoid function.

Next, in step 202, the learning data Y of the hidden layer is calculated by the following equation.

(Equation 9)

Next, in step 204,
Each coupling coefficient of the output layer is corrected. The correction amount is obtained by the following equation.

Δω ² _i, ³ _j (t) = P · Y ³ _j · f (I ² _i ) + Q · Δω ² _i, ³ _j (t−1) (10) where Δω ² _i, ³ _j (t) is the amount of change in the t-th calculation of the coupling coefficient between the j-th element of the output layer and the i-th element of the intermediate layer. Δω ² _i, ³ _j (t−1) is the previous correction amount of the coupling coefficient. P and Q are proportional constants. still,
As P is larger, the correction amount of the coupling coefficient is larger, so that the learning sensitivity or the learning speed (convergence speed) is increased, but the possibility of oscillation is more likely to occur. Also, the larger the Q, the more the previous correction amount is reflected, so that the stability of the change of the coupling coefficient becomes higher, and consequently the convergence becomes faster.

The corrected coupling coefficient is calculated by using the above correction amount.

[Expression 11] W ² _i, ³ _j + Δω ² _i, ³ _j (t) → W ² _i, ³ _j (11) Next, the process proceeds to step 206, where the coupling coefficient of each element of the intermediate layer is corrected. The correction amount of the coupling coefficient is obtained by the following equation, as in the case of the output layer.

[0024]

Δω ¹ _i, ² _j (t) = P · Y ² _j · f (I ¹ _i ) + Q · Δω ¹ _i, ² _j (t−1) (12) Therefore, the coupling coefficient is

## EQU13 _{## The} corrected coupling coefficient is obtained from W ¹ _i, ² _j + Δω ¹ _i, ² _j (t) → W ¹ _i, ² _j (13).

Next, in step 208, it is determined whether or not learning has been completed once for all input data to be learned. If learning has not been completed for all input data, the process proceeds to step 210, where the next input data and teacher data corresponding to the input data are set as learning target data. And step 200
Then, learning on the next input data is executed. In this way, when one learning is completed for all the input data, the determination result of step 208 is YES, and the process proceeds to step 212.

In step 212, it is determined whether or not the difference (error) between the output value of the neural network and the teacher signal has become sufficiently small. If the error is not sufficiently small, the process proceeds to step 214, where the first input data and the corresponding teacher data are set as learning target data in order to execute the second learning on all input data. You. Then, the process returns to step 200, and the learning operation described above is repeatedly executed. In this way, in step 212, the above-described learning operation is repeatedly executed until the error becomes equal to or less than the predetermined value. As a result, a neural network that is initially learned with respect to an initial wide range of events is completed.

3. Update of Database The data used for the learning of updating the neural network is configured in a database as shown in FIG.
Input _data, D 1, ..., a D _n, the corresponding teacher _data, E 1, ..., a E _n. The n pieces of input data and teacher data are data accumulated in the process of actually using the initial learning of the neural network or the neural network after the initial learning. This input data is defined as follows. The e data given to each of the e input elements is considered as a set of data. And
An arbitrary m-th set of input data is represented by D _m , and input data for a j-th input element belonging to the set is represented by d.
_Expressed by _mj . D _m represents a vector, and d _mj is a component of the vector. That is, D _m is defined by the following equation.

[0028]

Equation 14] _{D m = (d m1, d} m2, ..., d me-1, d me) (14) Further, n sets of input data _{D 1, D 2, ...,} D n-1, D n It is represented by Hereinafter, the input data group of all n sets is the input data group D
Is written.

[0029] _Similarly, E _1, ..., E _n is defined as follows. Regarding the output layer LO, the teacher data for the output from each of the g output elements is considered as a set of data. An arbitrary m-th set of teacher data is represented by _Em , and teacher data for the j-th output element belonging to the set is represented by em _m . E _m represents a vector, e
_mj is the component of the vector. That is, _Em is defined by the following equation.

[0030]

[Number 15] _{E m = (e m1, e} m2, ..., e mg-1, e mg) (15) In addition, n sets of teacher data is _{E 1, E 2, ...,} E n-1, E n It is represented by Hereinafter, all n sets of teacher data groups are the teacher data groups E
Is written. A count value _Cm is given to each data. The count value C _m, as described below, shows the degeneration number of data. Its initial value is 1.

Next, the procedure for updating the database will be described. FIG. 4 is a flowchart showing the procedure for updating the database. This database is updated by adding the newly added input data D _{n + 1} to the database storing the n input data groups D and the n teacher data groups E without increasing the data capacity of n data as a whole. And teacher data En _{+ 1} corresponding to the input data and the input data as learning data.

In step 300, as shown in FIG. 6A, the input data group (D
_1, ..., D _n ) and new input data D _{n + 1} , to consider an input data group (D _1, ..., D _{n + 1} ). Likewise, the teacher data group plus new teacher data _{E n + 1 (E 1,} ...,
En _{+ 1} ) is introduced. The counter value (the number of times of degeneration) C _{n + 1} for new data is 1. Next, step 3
02, an input data set (D) composed of arbitrary two data from the input data group (D _1, ..., D _{n + 1} ).
_p, D _q ). Next, in step 304,
The similarity Z _pq between the input data D _p and the input data D _q is calculated. In this embodiment, the similarity Z _pq is obtained by _comparing the D _p vector with the D _q
It is determined by the magnitude of the Euclidean distance between the vectors.

Therefore, the similarity Z _pq is defined by the following equation.

Equation 16] _{Z pq = | D p -D q} | (16) = ((d p1 -d q1) 2 + (d p2 -d q2) 2 + ... + (d pn -d qn) 2) 1 / ² Next, in step 306, whether the degree of similarity is calculated with respect to the combination of all of the two input data are determined. If the similarity has not been calculated for all the sets, in step 308, the index p, q of the selected input data is changed, and the process returns to step 302. From step 302, similar processing is repeatedly executed to calculate the similarity. Thus, in FIG.
As shown in (b), the similarity Z _pq of all data sets consisting of arbitrary two input data is calculated.

Next, in step 310, a data set (D _a , D _b ) in which the similarity Z _pq takes the minimum value Z _ab is determined from all the data sets. Next, in step 312, the input data D _a , D _b and the teacher data E _a , E _b corresponding to the input data are weighted and averaged using the counter values (the number of degeneration times) C _a , C _b as weighting coefficients. Input data D _h and weighted average synthesized teacher data E _h are calculated.

That is, the combined input data _Dh and the combined teacher data _Eh are calculated by the following equations.

_Dh = ( _Ca · _Da + _Cb · _Db ) / ( _Ca + _Cb ) (17)

[Number 18] _{E h = (C a · E} a + C b · E b) / (C a + C b) (18)

Next, at step 314, the counter values C _a and C _b are added, and the combined counter value (the number of times of degeneration) for the combined input data and the combined teacher data D _{h and} E _h is calculated.
_Ch is determined. Next, at step 316,
As shown in FIG. 6 (c), the input data group (D _1, ..., D _n, D
_{n + 1} ), the input data ( _{Da, Db} ) is deleted,
The weighted average synthetically synthetic input data D _h is added. Likewise, the teacher data group _{(E 1, ..., E n} , E n + 1) in the teacher data (E _a, E _b) is deleted, combined synthetic training data E _h is added by the weighted average .
Moreover, the combined input data and the synthetic training data D _h, the counter value corresponding to the E _h synthetic counter value (degenerate times) C _h
It is said.

As a result of such updating of the database, the number of input data and the number of teacher data are n. Even if new input data D _{n + 1} and new teacher data E _{n + 1} are added, the size of the database is not changed. It does not change. That is, the two input data (D _a, D _b ) are reduced to the combined input data D _h , and the two teacher data (E _a, E _b ) are reduced to the combined teacher data E _h . Then, the counter value (degeneration number) _Ch
Is the sum of the degenerate frequency of the current to the respective input data D _a and D _b. For example, when two input data for the first time degenerate, degenerate number C _h a composition input data is 2. Also, the input data whose degeneration frequency C _a is 2 and the degeneration frequency C
If _b is degenerated input data 3, degenerate number C _h a composition input data is 5.

Thus, in the process of using the neural network, no matter how many times input data and teacher data are newly generated, the number of input data and teacher data stored in the database does not exceed n. Using the n sets of input data group D and teacher data group E stored in the database, the update learning of the neural network is executed according to the above-described flowchart of FIG. Here, T _{j in} equation (8) is a certain teacher data E
_It means the j-th component e _mj of _m . Also, the teacher data _Em
At the time of learning regarding, the coefficient P in the equations (10) and (12) is given by the following equation.

Equation 19] _{P = α · C m (19} ) where, alpha is a coefficient, C _m is the count value of the teacher data E _m (degenerate times). As this factor P is greater, if the error is the same for the teacher data E _m, the variation of the coupling coefficient is increased. That is, it can be said that the learning data or the convergence speed is higher as the teacher data has a larger number of times of degeneration. As described above, by learning the coupling coefficient with the sensitivity corresponding to the number of times of degeneration, a learning effect based on teacher data having a large number of times of degeneration can be enhanced.

As described above, when one input data and teacher data are added to the n input data and teacher data, a set of two input data having the highest similarity in the input data and the input data The set of teacher data corresponding to the set is deleted and reduced to one combined input data and combined teacher data. Therefore, the n pieces of input data of the updated database become the most discrete set of input data at this stage, and the number of input data and the number of teacher data are fixed to n. Effective learning becomes possible.

Moreover, the combined input data and the combined teacher data are obtained by weighting and averaging the two data with the number of times of degeneration of each data, so that the components of the input data having a large number of times of degeneration are the components of the combined data. Is greatly reflected in. In other words, the current number of times of degeneration of input data (count value) represents the number of input data that have been degenerated up to the present stage and eventually changed to the input data. Therefore, taking a weighted average by weighting with the number of times of degeneration means that the characteristics of past degenerated input data are not deleted from the database at all, but are reflected in the synthesized input data at the top. I have. Furthermore, since the learning sensitivity is changed according to the number of times of degeneration of each teacher data, the learning effect is higher as the number of times of degeneration is larger. Therefore, learning a neural network using n sets of input data and teacher data is equivalent to learning a neural network with input data and teacher data that have accumulated all newly generated input data and teacher data. They are almost equivalent.

In the above embodiment, the similarity Z _pq is defined by the distance between the input data D _p and the input data D _q , but the similarity Z _pq may be defined by using various similarities used in the clustering method. Is also good. In the above-described embodiment, a free area capable of storing one set of data is created from a database having a capacity capable of storing n data sets. However, when the number of pairs of input data and teacher data newly used for update learning is plural, the necessary number of pairs of input data and teacher data are degenerated in order from the pair having the highest similarity between the input data. You may do so. Further, in the above embodiment, the coefficient P in the equations (10) and (12) is changed in proportion to the number of times of degeneration of the teacher data, but the relationship between this coefficient P and the number of times of degeneration is set by an arbitrary function. You may. Furthermore, since the correction amount of the coupling coefficient may be corrected so as to increase as the number of times of degeneration increases, the coefficient Q in Equations (10) and (12) is set to a smaller value as the number of times of degeneration increases. Is also good.

[Brief description of the drawings]

FIG. 1 is a configuration diagram showing a configuration of a neural network according to a specific embodiment of the present invention.

FIG. 2 is a flowchart showing a calculation procedure of the neural network according to the embodiment.

FIG. 3 is a flowchart showing a learning procedure of the neural network according to the embodiment.

FIG. 4 is an exemplary flowchart showing a procedure for updating a database having input data and teacher data used for learning to update the neural network according to the embodiment.

FIG. 5 is a configuration diagram showing a data configuration of a database used for update learning of the neural network according to the embodiment.

FIG. 6 is an explanatory view showing the concept of a database update procedure used for neural network update learning according to the embodiment;

[Explanation of symbols]

 10 ... Neural network LI ... Input layer LM ... Intermediate layer Lo ... Output layer

──────────────────────────────────────────────────続 き Continuation of the front page (56) References JP-A-4-184668 (JP, A) (58) Fields investigated (Int. Cl. ⁷ , DB name) G06N 1/00-7/00 G06G 7 / 60 JICST File (JOIS) CSDB (Japan Patent Office)

Claims (1)

(57) [Claims] 1. A method for learning a neural network using an updated database while updating a database storing input data and corresponding teacher data, wherein the input data is arbitrarily selected from the input data. For all sets of two input data, a similarity indicating the degree of similarity between the two input data is calculated, and the two sets of input data having the highest similarity are calculated as: The two input data are reduced to one input data, and the two teacher data corresponding to the two input data are reduced to one teacher data based on the two teacher data. The generated number of times of degeneration of the input data or the teacher data is calculated based on the past number of times of degeneration of two pieces of degenerated data. The number of times of degeneration is stored for each of the input data or the teacher data, and at the time of learning the coupling coefficient of the neural network using the teacher data, in the correction operation of the coupling coefficient using each teacher data, A neural network learning method, wherein the correction amount of the coupling coefficient is changed according to each number of times of degeneration.