JP3236635B2 - 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, it relates to a method for storing input data and teacher 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.

The present invention has been made to solve the above-mentioned problem, and an object of the present invention is to perform efficient learning of a neural network which requires a small storage capacity.

[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, the input data and the corresponding teacher data
For each data set, each set has a counter value indicating the number of times of degeneration.
Then, for all of the sets composed of two input data arbitrarily selected from the input data, a similarity indicating the degree to which the two input data are similar to each other is calculated,
The two sets of input data with the highest similarity are
Weighted average by the counter value and reduced to one input data
So, the two training data corresponding to the two input data of that, weighted average by degenerated to one teacher <br/> data by respective counter values, the newly generated input data by degeneration
Counter value corresponding to the set of data and the corresponding teacher data
Is defined as the sum of two counter values serving as a source of degeneration, controlling the data stored in the database so that the amount of stored data does not exceed a predetermined amount, and sequentially learning the neural network. Features.

[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. At that time, input data and corresponding
Based on the counter value of each set of
Degenerate by weighted average and newly generated by degeneracy
Of the input data and the corresponding teacher data
Counter value as the sum of the two counter values that
I do.

[0009]

By controlling the storage capacity of the database, it is possible to prevent the amount of stored data from exceeding 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. Reduced input data and reduced teacher data
Data is used to reduce the two data
Weighted with the counter value indicating the number of withdrawals and weighted average
Components of the input data with a large number of reductions are reduced.
This is largely reflected in the data components. Such shrinkage
New data using the input data and the teacher data
Learning a neural network can
Input data and training
Train neural networks with guru data
Is almost equivalent to Therefore, effective learning of the neural network is achieved.

[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 Neural Network This neural network performs the initial learning as shown in FIG.
Learning is performed according to the procedure shown in FIG. 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 ,
Granted from outside. F ^′ (x) is a derivative of the sigmoid 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. Therefore, the coupling coefficient is

[0023]

The corrected coupling coefficient is obtained from 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, the correction amount Δ of the coupling coefficient
Whether or not the coupling coefficient has converged is determined by determining whether or not ω has become equal to or less than a predetermined value. If the coupling coefficients have not converged, 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 the input data. . Then, the process returns to step 200, and the learning operation described above is repeatedly executed. In this way, in step 212, the above learning operation is repeatedly executed until the correction amount Δω of the coupling coefficient becomes equal to or less than the predetermined value and the coupling coefficient converges. 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
Seeking in the magnitude of the displacement vector between the vectors (D _p -D _q).

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, regarding the input data D _a , D _b and the teacher data E _a , E _b corresponding to the input data, the counter values C _a ,
Composite input data D weighted by using C _b as a weighting factor
_h and the 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, in step 314, are summed counter value C _a and C _b is synthesized input data and the synthetic training data D _h, synthetic counter value C _h for E _h is determined. Next, in step 316, the input data (D _a, D _b ) is deleted from the input data group (D _1, ..., D _n, D _{n + 1} ) as shown in FIG. 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 is a synthesized counter value C _h.

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 C _h 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. Further, if the input data of degenerate times C _a is input data degenerated number C _b of 2 3 by degeneration, degeneracy 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.

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.

The combined input data and the combined teacher data are obtained by weighting the two data with the number of times of degeneration for each data and obtaining a weighted average. 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. In other words, as described above, the learning of the neural network using the n sets of input data and the teacher data by the degeneration processing requires input data and teacher data in which all newly generated input data and teacher data are accumulated. This is almost equivalent to learning a neural network.

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. Further, in the above embodiment, the synthetic input data and the synthetic teacher data are generated by the weighted average using the number of times of degeneracy and the number of times of degeneracy. Alternatively, synthetic teacher data may be generated. 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.

[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

Continuation of the front page (72) Inventor Moriaki Sakakura 1-1-1 Asahimachi, Kariya City, Aichi Prefecture Inside Toyota Koki Co., Ltd. (56) References JP-A-4-184668 (JP, A) JP-A-3-18965 ( 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 in which input data and corresponding teacher data are stored , wherein a set of the input data and the corresponding teacher data is Each group
Has a counter value indicating the number of times of degeneration, and for all sets composed of two input data arbitrarily selected from the input data, the degree to which the two input data are similar to each other calculates the degree of similarity representing a highest set of two input data of the similarity, it
Is then weighted mean by said counter value is degenerated to one input data, the two teaching corresponding to the two input data of that
The teacher data, the weighted average by each of the counter value
Te is degenerated to one teacher data, the teacher and the corresponding newly generated input data by degeneration
The counter value corresponding to the data set is set to 2
A learning method, wherein the neural network is sequentially learned by controlling data stored in the database so that the amount of accumulated data does not exceed a predetermined amount as a sum of two counter values .