JPH05113219A - Cooking equipment - Google Patents

Abstract

PURPOSE:To enable an indirect sensing of a finished state of a cooked item to be performed by a method wherein a temperature of the cooked item is assumed in an actual time in reference to an environmental physical amount in a heating chamber and a specific physical amount of the cooked item. CONSTITUTION:An environmental physical amount sensing means 6 detects an atmospheric temperature within a heating chamber by a thermistor. Means 12 for detecting a specific physical amount of the cooked item detects and follows up a variation of weight of the cooked item with a strain gauge as its value is varied while the heating operation is continue. A temperature assuming means 13 assumes a surface temperature, a central part temperature and a rear surface temperature of the cooked item in response to outputs of an environment physical amount sensing means 6, the means 12 for detecting a specific physical amount of the cooked item, a voltage level sensing means 7, a time counting means 8 and a category selection key 10. The control means 5 controls a heating and supplying means 3 in response to the output of the temperature assuming means 13. In this way, the temperature increasing in the cooked item is indirectly detected, thereby a finished state of the cooked item can be acknowledged.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a cooking utensil for automatic cooking in a microwave oven, gas oven, roaster and the like.

[0002]

2. Description of the Related Art Conventionally, this type of cooking utensil (here, a roaster) has been constructed as shown in FIG. Less than,
The configuration will be described.

As shown in the figure, a cooking utensil 1 is composed of a heating chamber 2 in which a food is put, a heating supply means (heater) 3 for heating the food, a thermistor for detecting the internal temperature of the heating chamber 2, and the like. The temperature detecting means 4 and the control means 5 for controlling the heating supply means 3 based on the information from the temperature detecting means 4. In order to automatically cook with such a structure, it is necessary to know the weight of the food, the initial temperature, and the like. Therefore, the output voltage gradient of the temperature detecting means 4 is measured for several minutes after the power is turned on, and if the gradient is steep, it is determined that the weight of the cooked food is light, and if the gradient is gentle, the weight is large, and the voltage gradient is determined. The optimum cooking time was determined by multiplying the constant K by The output voltage characteristic of the temperature detecting means 4 is shown in FIG. FIG. 12A shows a light weight, and FIG. 12B shows a heavy weight. And I did a lot of cooking experiments and decided the constant.

[0004]

In such a conventional cooking utensil (here, a roaster), the gradient of the ambient temperature in the heating chamber is detected, and the cooking product (for example,
The cooking time was decided based on the weight of the (fried fish), so there was considerable variation in the completion of cooking. For example, the initial temperature in the heating chamber is not always low, and when cooking is performed immediately after finishing cooking, the initial temperature in the heating chamber becomes very high. In this case, when a heavy food is cooked, the output voltage characteristic of the temperature detecting means 4 is shown in FIG.
The temperature inside the heating chamber drops for a moment. This is because the temperature inside the heating chamber is absorbed by the food because the temperature inside the heating chamber is high even when cooking is started. In such a case, it was difficult to determine the optimum cooking time by the method described above. Further, since the heating supply means 3 is a heater, the fluctuation of the commercial power supply voltage considerably affects the completion of cooking. In other words, the completion of cooking varies considerably depending on the environment at the time of starting cooking (type of food, initial temperature in heating chamber, initial temperature of food, power supply voltage, etc.). In addition, when it comes to grilling fish, it is important that the surface is baked, but the temperature inside the fish will rise by 6
It is said that 0 ° C to 70 ° C is the best. In consideration of such a situation, there is a problem that it is very difficult to detect the completion of cooking in terms of the surface burnt condition and the internal temperature rise.

The present invention is intended to solve the above-mentioned problems. The temperature of a cooked food is estimated in real time by estimating the physical quantity of the environment inside the heating chamber, which can be actually measured and detected, and the physical quantity specific to the cooked food. The purpose is to indirectly detect the completion.

[0006]

In order to achieve the above object, the present invention provides a heating chamber for storing a food for cooking, a heating supply means for heating the food, and an environment in the heating chamber. Environmental physical quantity detection means for detecting, and cooking product specific physical quantity detection means for detecting the specific physical quantity of the cooking product,
Based on the outputs of the environmental physical quantity detection means and the cooking-specific physical quantity detection means, the surface temperature of the cooking product, the central temperature,
The backside temperature is composed of a temperature estimating means for estimating at least one of the backside temperatures, and a control means for controlling the heating and supplying means based on the output of the temperature estimating means. The temperature estimating means comprises a plurality of neural elements. It has a hierarchical neural network model means which internally has a plurality of coupling weight coefficients of a fixed neural network for estimating the temperature of a cooked food obtained by a method simulating the constructed neural network.

[0007]

The present invention is actually cooked by the above-mentioned means for solving problems by inputting the environmental information in the heating chamber from the environmental physical quantity detecting means and the specific physical information from the cooking physical quantity detecting means to the temperature estimating means. The temperature estimation means having the neural network model means for learning all the actual cooking environment and having the fixed connection weighting coefficient as the weighting coefficient is at least one of the surface temperature, the central temperature and the back surface temperature of the cooked food. Estimate from moment to moment. The control means controls the heating supply means (heater in the electric roaster) based on the output of the temperature estimation means, and indirectly detects the temperature rise of the cooked product, thereby recognizing the completion. To do.

[0008]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of the present invention will be described below with reference to FIGS. The same components as those in the conventional example are designated by the same reference numerals and the description thereof will be omitted.

In this embodiment, an example in which an electric roaster for grilling fish etc. is applied as a cooking tool will be described. Figure 1
As shown in, the environmental physical quantity detection means 6 detects the environment inside the heating chamber. In this embodiment, the ambient temperature in the heating chamber is detected, and it is composed of a thermistor or the like. The voltage level detecting means 7 detects the voltage level of the commercial power supply voltage. The timekeeping means 8 counts the time since the power was turned on. The operating means 9 comprises a category selection key 10 for selecting a category of food and a cooking start key 11 for starting and stopping cooking. The cooking physical quantity detecting means 12 detects a physical quantity peculiar to the food, and in the present embodiment, it is composed of a weight sensor (strain gauge) for detecting the weight of the food. The weight of the cooked food changes with time because steam is generated as it is heated. The temperature estimating means 13 estimates the surface temperature, the center temperature, and the back surface temperature of the cooked food based on the outputs of the environmental physical quantity detecting means 6, the cooked product specific physical quantity detecting means 12, the voltage level detecting means 7, the clocking means 8, and the category selection key 10. The control means 5 controls the heating supply means 3 based on the output of the temperature estimation means 13. The heating supply means 3 is a heater and is arranged in the heating chamber 2. Further, reference numeral 14 is a display means for displaying the remaining time of cooking and the like, which comprises a fluorescent display tube. Further, reference numerals 15, 16 and 17 denote A / D conversion means for converting the outputs of the environmental physical quantity detection means 6, the voltage level detection means 7 and the cooking product specific physical quantity detection means 12 into digital. FIG. 2 shows the configuration of the display unit and the operation unit.

Since the solving means used in the conventional control method cannot be applied to the means constituting the temperature estimating means 13, the means for simulating a neural network which is optimal as a multidimensional information processing method is used. There is. In the method that imitates the neural network, a method of using a plurality of connection weight coefficients of the neural network for estimating the temperature (surface temperature, central temperature, back surface temperature) of the cooked food as a fixed table and leaving the learning function There are ways to adapt to the environment and users. The present embodiment is provided with a temperature estimating means 13 having a neural network model means having therein a fixed coupling weighting coefficient for estimating the temperature of a food product obtained by a method simulating a neural network.

Factors that affect the completion of the cooked food include the initial temperature in the heating chamber, the initial temperature of the cooked food, the type (category) of the cooked food, the voltage level of the commercial power supply voltage, and the like. The finished product fluctuates greatly due to these factors.

The fixed weighting coefficient fixed in the neural network for estimating the temperature of the cooked food is the surface temperature of the cooked food when cooked in the actual cooking environment (environment in which various factors described above are combined). , The center temperature, the backside temperature, the ambient temperature in the heating chamber, and how the weight change of the food changes, and collects the environmental data, the ambient temperature data in the heating chamber, the weight change data, and the temperature of the food ( It can be obtained by making the neural network model means learn the correlation with the data of the front surface, the center, and the back surface. As a neural network model means to be used, reference 1 (D.E.
"PDP model" translated by Shunichi Amari, written by Ramelhart and 2 others
Sangyo Tosho Co., Ltd. (1989), Reference 2 (Kaoru Nakano and 7 others, "Basics of Neurocomputers", Corona Publishing Co., Ltd.,
P102, 1990) and Japanese Examined Patent Publication No. 63-55106. Hereinafter, the configuration and operation of a concrete neural network schematic means will be described by taking a multilayer perceptron using an error backpropagation method as the most well-known learning algorithm described in Document 1 as an example.

FIG. 3 is a conceptual diagram of a neural element which is a constituent unit of the neural network model means. In FIG. 3, 21 to 2
N is a pseudo synapse coupling converter simulating synaptic coupling of nerves, and 2a is pseudo synapse coupling converters 21 to 2N.
2b is a set nonlinear function, for example, a sigmoid function whose threshold is h, f (y, h) = 1 / (1 + exp (-y + h)) (Equation 1 ) Is a non-linear converter for non-linearly converting the output of the adder 2a. Although omitted because the drawing is complicated, an input line for receiving a correction signal from the correction means is connected to the pseudo synapse coupling converters 21 to 2N and the non-linear converter 2b. Further, the pseudo synapse coupling converters 21 to 2N serve as coupling weight coefficients of the neural network schematic unit. This neural element has two types of operation modes, a signal processing mode and a learning mode.

The operation of each mode of the neural element will be described below with reference to FIG. First, the operation of the signal processing mode will be described. Neural elements are N inputs X1 to X
It receives n and outputs one output. i-th input signal Xi
Is the i-th pseudo-synaptic coupling converter 2 shown by a square
i is converted to Wi · Xi. N signals W1 · X1 converted by the pseudo synapse coupling converters 21 to 2N
Wn · Xn enters the adder 2a, the addition result y is sent to the nonlinear converter 2b, and becomes the final output f (y, h). Next, the operation of the learning mode will be described. In the learning mode, the conversion parameters W1 to Wn and h of the pseudo synapse coupling converters 21 to 2N and the non-linear converter 2b are received, and the correction signals representing the correction parameter correction amounts ΔW1 to ΔWn and Δh are received from the correction means. , Wi + ΔWi; i = 1, 2, ..., N h + Δh (Equation 2)

FIG. 4 is a conceptual diagram of a signal converting means constituted by connecting four neural elements in parallel. Needless to say, the following description does not specify that the number of neural elements constituting this signal converting means is four. In FIG. 4, 211 to 244 are pseudo synapse coupling converters,
201 to 204 are addition nonlinear converters that combine the adder 2a and the nonlinear converter 2b described in FIG. 4, the illustration is omitted because the drawing is complicated as in FIG. 3, but the input lines for receiving the correction signal from the correction means are pseudo synapse coupling converters 211 to 244 and an addition nonlinear converter 20.
It is connected to 1-204. The pseudo synapse coupling converters 211 to 244 also serve as coupling weight coefficients. Regarding the operation of this signal conversion means, the operation of the neural element described in FIG. 3 is performed in parallel.

FIG. 5 is a block diagram showing the configuration of the signal processing means when the error back-propagation method is adopted as the learning algorithm, and 31 is the above-mentioned signal converting means. However,
Here, M neural elements for receiving N inputs are arranged in parallel. Reference numeral 32 is a correction means for calculating the correction amount of the signal conversion means 31 in the learning mode. Hereinafter, the operation when learning the signal processing means will be described with reference to FIG. The signal converting means 31 has N inputs S
Upon receiving _in (X), it outputs M outputs S _out (X).
The correction means 32 includes an input signal S _in (X) and an output signal S _out.
Upon receiving (X), the process waits until M error signals δ _i (X) are input from the error calculating means or the signal converting means in the subsequent stage. The error signal δ _i (X) is input and the correction amount is ΔW _ij = δ _i (X) · S _iout (X) · (1−S _iout (X)) · S _jin (X) (i = 1 to N , J = 1 to M) (formula 3) is calculated, and the correction signal is sent to the signal conversion means 31. The signal conversion means 31 modifies the conversion parameters of the internal neural elements according to the learning mode described above.

FIG. 6 is a block diagram showing the structure of a multilayer perceptron using a neural network model.
X, 31Y, and 31Z are signal conversion means composed of K, L, and M neural elements, respectively, and are 32X, 32Y, and 3X.
2Z is a correction means, and 33 is an error calculation means. The operation of the multi-layer perceptron configured as described above will be described with reference to FIG. Signal processing means 3
In 4X, the signal conversion means 31X receives the input S
_{Receives iin} (X) (i = 1 to N) and outputs S _jout (X)
(J = 1 to k) is output. The correction means 32X uses the signal S
_The error signal δ is received by receiving _iin (X) and the signal S _jout (X).
Wait until _j (X) (j = 1 to k) is input. The same processing is performed in the signal processing means 34Y and 34Z, and the final output _Shout (Z) from the signal converting means 31Z.
(H = 1 to M) is output. Final output _Shout (Z)
Is also sent to the error calculation means 33. Error calculation means 33
, The error from the ideal output T (T1, ..., TM) is calculated based on the squared error evaluation function COST (Equation 4), and the error signal δ _h (Z) is corrected by the correction means. 32Z
Sent to.

[0018]

[Equation 1]

However, η is a parameter that determines the learning speed of the multilayer perceptron. Next, when the evaluation function is a squared error, the error signal is δh (Z) = − η · (s _hout (Z) −T _h ) (Equation 5). According to the procedure described above, the correction means 32Z calculates the correction amount ΔW (Z) of the conversion parameter of the signal conversion means 31Z, calculates the error signal to be sent to the correction means 32Y based on (Equation 6), and corrects it. The signal ΔW (Z) is sent to the signal converting means 31Z, and the error signal δ (Y) is corrected by the correcting means 32.
Send to Y. The signal converting means 31Z uses the correction signal ΔW (Z).
Modify internal parameters based on. The error signal δ (Y) is given by (Equation 6).

[0020]

[Equation 2]

[0021] Here, W _ij (Z) signal converting means 31Z
Is a conversion parameter of the pseudo synapse coupling converter of. Hereinafter, similar processing is performed in the signal processing means 34X and 34Y. By repeating the above procedure called learning, the multi-layer perceptron produces an output that closely approximates the ideal output T when given an input. In the above description, the three-stage multi-layer perceptron is used, but this may be any number of stages. In addition, reference 1
The modification method of the conversion parameter h of the non-linear conversion means in the signal conversion means and the method of accelerating learning known as the inertia term are omitted for simplification of the description, but this omission is described below. It does not bind the invention.

In this way, the neural network model means uses the environmental data (the initial temperature in the heating chamber, the commercial power supply voltage level, the type of food, the initial temperature of the food, etc.) when cooking and the ambient temperature data in the heating chamber. By learning the relationship between the weight change data of the cooking product and the temperature (front surface, center, back surface) data of the cooking product, it is possible to naturally express the control method that is not easy to describe with simple rules. In this embodiment, the temperature estimation means 13 is configured by incorporating the information thus obtained. Specifically, the signal converting means 31X, 31Y of the multi-layer perceptron after sufficiently learning is completed.
The temperature estimating unit 13 is configured by using only 31Z as a neural network schematic unit. The data actually learned will be described.

FIG. 7 shows the characteristics when cooking when the initial temperature of the heating chamber 2 is low, the commercial power supply voltage is 100 V, the type of food is one horse mackerel, and the initial temperature of the food is about 10 ° C. It was done. FIG. 7A shows the environmental physical quantity detection means 6.
7 (b) shows the change in weight of the food, FIG. 7 (c) shows the surface temperature of the food, and FIG. 7 (d) shows the center temperature of the food. FIG.7 (e) has shown the change of the back surface temperature of a cooked material. The temperature of the cooked food is measured with a thermocouple or the like. FIG. 8 shows the characteristics when cooking when the initial temperature of the heating chamber 2 is high, the commercial power supply voltage is 100 V, the type of food is one horse mackerel, and the initial temperature of the food is approximately 10 ° C. is there. FIG. 9 shows the heating chamber 2.
The initial temperature is low, the commercial power supply voltage is 100 V, the type of food is four horse mackerels, and the initial temperature of the food is approximately 10 ° C. FIG. 10 shows the characteristics when cooking when the initial temperature of the heating chamber 2 is high, the commercial power supply voltage is 100 V, the type of food is four horse mackerels, and the initial temperature of the food is approximately 10 ° C. is there.

8 (a) to 8 (e), 9 (a) to 9 (e), and 10 (a) to 10 (e) are shown in FIG. 7 (a).
~ It corresponds to Fig. 7 (e), respectively. It can be seen that the output voltage change (environmental temperature in the heating chamber) of the environmental physical quantity detection unit 6 and the output voltage change of the cooking product specific physical quantity detection unit 12 are different depending on the initial temperature in the heating chamber and the amount of the cooking product. Similarly, when the power supply voltage is changed, the output changes differently even when the type of food is changed. Such an experiment was similarly carried out for all combinations of the actual cooking environments. Then, the experimental data was input to the neural network model means for learning. That is, to the neural network model means, the ambient temperature information in the heating chamber of the environmental physical quantity detecting means 6, the ambient temperature information one minute before the present time as the ambient temperature gradient information, and the cooked product of the cooked product specific physical quantity detecting means 12 Weight information, weight data one minute before the present time as weight change information, commercial power source voltage level information of the voltage level detection means 7, elapsed time information after power-on obtained from the time counting means 8, and category selection key 7 information of category information obtained from 10 and 3 information of surface temperature information, central temperature information, and back surface temperature information of the cooking product as ideal outputs are input and learned, and signal conversion means 31X in the neural network model means, 31Y and 31Z are established, and they are incorporated in the temperature estimation means 13 as a neural network schematic means.

Next, the operation will be described based on the block diagram shown in FIG. First, put the food in the heating chamber,
A cooking category is selected with the category selection key 10 of the operation means 9. Then, cooking is started by the cooking start key 11. The category information is input to the temperature estimation means 13 via the control means 5. The control means 5 outputs a signal to start timing to the timing means 8 and also outputs a heating start signal to heat the heating supply means 3. The timing information of the timing means 8 is input to the temperature estimation means 13. The environmental physical information (atmosphere temperature information) in the heating chamber is digitally converted from the output of the environmental physical quantity detection means 6 by the A / D conversion means 15 and input to the temperature estimation means 13 every moment. The voltage level information of the commercial power supply voltage from the voltage level means 7 is digitally converted by the AD conversion means 16 and input to the temperature estimation means 13. Further, the weight information from the cooking product specific physical quantity detection means 12 is also used as the A / D conversion means 1
Digitally converted at 7 and input to the temperature estimation means 13. The temperature estimation means 13 receives these input signals,
Based on the information, the surface temperature, the central temperature, and the back surface temperature of the food are estimated moment by moment, and the information is output to the control means 5. The control means 5 operates so as to control the heating supply means 3 based on this estimated temperature information.

Further, although the control means 5, the timing means 8 and the temperature estimation means 13 are all constructed by a 4-bit microcomputer, it is of course possible to construct them by one microcomputer. The temperature estimation means 1
Reference numeral 3 indicates temperature gradient information of the environmental physical quantity detection means 6 (two pieces of information at the present time and one minute ago), and the cooking product specific physical quantity detection means 12
Weight information (2 pieces of information at the present time and 1 minute ago), voltage level information of the commercial power supply voltage obtained by the voltage level detection means 7, elapsed time information from the time of power-on obtained by the time counting means 8, and a category selection key. Although 7 items of the category information of the cooking product obtained from 10 are input, this limitation does not restrict the present invention. Also, although ambient temperature information was used as environmental physical quantity information, smoke information, brown color information, humidity information, and steam information can also be applied, and in addition to weight information, shapes and the like can also be applied as cooking-specific physical quantities. The estimation accuracy is further improved by combining. Further, although the electric roaster is used as the cooking utensil in the present embodiment, it may be a microwave oven or a gas oven, in particular,
In a microwave oven, it seems to be the most suitable when thawing foods. In other words, since the temperature of the cooked food can be estimated, it suffices to finish the cooking in the vicinity (around 0 ° C.) where the phase transition from solid (ice) to liquid (water) occurs.
At this time, the environmental physical information may be the ambient temperature,
Information on the amount of absorption of radio waves (electrolytic intensity) of cooked foods is optimal.

As described above, according to the present embodiment, the temperature estimation incorporating the neural network model means having a plurality of fixed coupling weight coefficients of the neural network already learned in the environment of the heating chamber where the cooking is actually performed Since it is configured with means,
The finished state of the cooked food can be detected by the surface temperature, the central temperature, and the backside temperature, and the cooked state can be improved more than ever before, which is most suitable for automatic cooking.

[0028]

As is apparent from the above embodiments, according to the present invention, there is provided a heating chamber for storing food to be cooked,
Heating supply means for heating the cooking product, environmental physical quantity detecting means for detecting the environment in the heating chamber, cooking unique physical quantity detecting means for detecting the unique physical quantity of the cooking object, the environmental physical quantity detecting means and the cooking Since the temperature estimation means for estimating the temperature of the cooking product based on the output of the object-specific physical quantity detection means and the control means for controlling the heating supply means of the previous period based on the output of the temperature estimation means, For recognition, the actual temperature of the cooked food can be indirectly detected. Therefore, it is possible to improve the finished state of cooking as compared with the conventional method in which the optimum cooking time is determined from the gradient of the atmospheric temperature and the like.

Further, the temperature estimating means is the surface temperature of the food,
At least one of the center temperature and the back surface temperature is estimated, so that the entire finished state of the cooked food from the front surface to the inside can be known.

Further, the temperature estimation means is a fixed neural network for estimating the temperature (front surface, center, back surface temperature) of the food obtained by a method simulating a neural network composed of a plurality of neural elements. Since it has a neural network schematic means having a plurality of coupling weight coefficients of, or has a hierarchical neural network schematic means constructed by combining layers composed of a plurality of neural elements in multiple layers, The temperature of the cooked food can be estimated regardless of the initial temperature in the heating chamber, the initial temperature of the cooked food, the amount of the cooked food, etc., and automatic cooking is possible.

[Brief description of drawings]

FIG. 1 is a configuration block diagram of a cookware according to an embodiment of the present invention.

FIG. 2 is a configuration diagram of an operation unit and a display unit used in the cooking utensil.

FIG. 3 is a conceptual diagram of a neural element that is a constituent unit of a neural network schematic means used in the cooking utensil.

FIG. 4 is a conceptual diagram of a signal conversion means composed of neural elements used in the cooking utensil.

FIG. 5 is a block diagram of a signal processing unit that employs an error backpropagation method as a learning algorithm used for the cooking utensil.

FIG. 6 is a block diagram showing a configuration of a multilayer perceptron using a neural network schematic means used in the cooking utensil.

7A to 7E are views showing an example of experimental data of the cooking utensil.

8A to 8E are views showing another example of the experimental data of the cooking utensil.

9A to 9E are views showing another example of the experimental data of the cooking utensil.

FIG. 10 (a) to (e) are views showing another example of experimental data of the cooking utensil.

FIG. 11 is a configuration block diagram of a conventional cooking utensil.

FIG. 12 (a) and (b) are views showing an example of experimental data of a conventional cooking utensil.

FIG. 13 is a diagram showing another example of experimental data of conventional cooking utensils.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Cooking utensil 2 Heating chamber 3 Heating supply means 5 Control means 6 Environmental physical quantity detection means 7 Cooking physical property quantity detection means 13 Temperature estimation means

Claims (4)

[Claims] 1. A heating chamber for storing cooked foods for cooking, a heating supply means for heating the cooked foods, an environmental physical quantity detecting means for detecting an environment in the heating chambers, and an inherent physical quantity of the cooked foods. Means for detecting an inherent physical quantity of a food to be detected,
The environmental physical quantity detecting means, the temperature estimating means for estimating the temperature of the cooking product based on the output of the cooking physical quantity detecting means, and the control means for controlling the heating supply means based on the output of the temperature estimating means. kitchenware. 2. The cooking utensil according to claim 1, further comprising a temperature estimating means for estimating at least one of a surface temperature, a central temperature and a back surface temperature of the cooked food. 3. The temperature estimating means internally includes a plurality of coupling weight coefficients of a fixed neural network for estimating a temperature of a food obtained by a method simulating a neural network composed of a plurality of neural elements. 2. The cooking utensil according to claim 1, further comprising a neural network schematic means possessed by. 4. The cooking utensil according to claim 1, wherein the temperature estimating means includes a hierarchical neural network schematic means constructed by combining a plurality of layers composed of a plurality of neural elements in a multilayered manner. ..