Information processing device, information processing method, and recording medium

Abstract

This information processing device (1) comprises: an acquisition means (50) which acquires a plurality of elements included in series data; a calculation means (100) which calculates a likelihood ratio, which indicates the likelihood of a class to which the series data belongs, from at least two consecutive elements among the plurality of elements by using an activation function of which the value range is wider than [-1, 1], a change in output value is slower than that in an input value, and the gradient at the original point does not diverge; and a classification means (200) which classifies, on the basis of the likelihood ratio, the series data into at least one class among a plurality of classes. According to this information processing device, it is possible to achieve both highly accurate estimation of the likelihood and training stability.

Description

Information processing device, information processing method, and recording medium

[0001] The present disclosure relates to the technical fields of an information processing device, an information processing method, and a recording medium.

[0002] One known example of this type of device is one that classifies sequential data using likelihood ratios. For example, Patent Document 1 discloses a device that sequentially acquires and analyzes multiple elements included in the sequential data to classify the sequential data into one of multiple predetermined classes.

[0003] As other related techniques, for example, Patent Document 2 discloses learning related to likelihood ratio calculation using a log-sum-exponential loss function. Patent Document 3 discloses estimating a log likelihood ratio using KLIEP (Kullback-Leibler Importance Estimation Procedure), which is an estimation method that minimizes the KL distance.

[0004] International Publication No. 2020 / 194497 International Publication No. 2022 / 157973 International Publication No. 2021 / 229663

[0005] This disclosure aims to improve upon the related art discussed above.

[0006] One aspect of the information processing device disclosed herein includes an acquisition means for acquiring multiple elements included in sequence data; a calculation means for calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, using an activation function that has a value range wider than [-1, 1], an output value that changes more gradually than an input value, and a gradient that does not diverge at the origin, from at least two consecutive elements among the multiple elements; and a classification means for classifying the sequence data into at least one class among multiple candidate classes based on the likelihood ratio.

[0007] One aspect of the information processing method disclosed herein involves using at least one computer to acquire multiple elements included in sequence data, calculate a likelihood ratio indicating the likelihood of a class to which the sequence data belongs from at least two consecutive elements among the multiple elements using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge, and classify the sequence data into at least one class among multiple candidate classes based on the likelihood ratio.

[0008] One aspect of a recording medium of this disclosure is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which includes acquiring multiple elements included in sequence data, calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs from at least two consecutive elements among the multiple elements using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge, and classifying the sequence data into at least one class among multiple candidate classes based on the likelihood ratio.

[0009] 1 is a block diagram showing a hardware configuration of an information processing device according to a first embodiment. FIG. 2 is a block diagram showing a functional configuration of the information processing device according to the first embodiment. FIG. 3 is a flowchart showing a flow of operation of the information processing device according to the first embodiment. FIG. 4 is a graph showing an example of a likelihood ratio calculated by the information processing device according to the first embodiment, together with a comparative example. FIG. 5 is a graph showing an example of an activity function used in the information processing device according to the second embodiment. FIG. 6 is a graph showing an example of an activity function used in the information processing device according to the third embodiment. FIG. 7 is a block diagram showing a functional configuration of an information processing device according to a fourth embodiment. FIG. 8 is a flowchart showing a flow of operation of the information processing device according to the fourth embodiment. FIG. 9 is a block diagram showing a functional configuration of an information processing device according to a fifth embodiment. FIG. 10 is a flowchart showing a flow of a likelihood ratio calculation operation in the information processing device according to the fifth embodiment.

[0010] Hereinafter, embodiments of an information processing device, an information processing method, and a recording medium will be described with reference to the drawings.

[0011] First Embodiment An information processing apparatus according to a first embodiment will be described with reference to FIGS. 1 to 4. FIG.

[0012] (Hardware Configuration) First, the hardware configuration of the information processing apparatus according to the first embodiment will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the hardware configuration of the information processing apparatus according to the first embodiment.

[0013] 1 , an information processing device 10 according to the first embodiment includes a processor 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, and a storage device 14. The information processing device 10 may further include an input device 15 and an output device 16. The processor 11, RAM 12, ROM 13, storage device 14, input device 15, and output device 16 are connected to each other via a data bus 17.

[0014] The processor 11 loads a computer program. For example, the processor 11 is configured to load a computer program stored in at least one of the RAM 12, the ROM 13, and the storage device 14. Alternatively, the processor 11 may load a computer program stored in a computer-readable storage medium using a storage medium reading device (not shown). The processor 11 may acquire (i.e., load) the computer program from a device (not shown) located outside the information processing device 10 via a network interface. The processor 11 controls the RAM 12, the storage device 14, the input device 15, and the output device 16 by executing the loaded computer program. In particular, in this embodiment, when the processor 11 executes the loaded computer program, a functional block that performs class classification based on likelihood ratios is realized within the processor 11. In other words, the processor 11 may function as a controller that executes each control in the information processing device 10.

[0015] The processor 11 may be configured as, for example, a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), a demand-side platform (DSP), an application-specific integrated circuit (ASIC), or a quantum processor. The processor 11 may be configured as one of these, or may be configured to use multiple processors in parallel.

[0016] The RAM 12 temporarily stores computer programs executed by the processor 11. The RAM 12 temporarily stores data that the processor 11 temporarily uses while it is executing the computer programs. The RAM 12 may be, for example, a dynamic random access memory (D-RAM) or a static random access memory (SRAM). Alternatively, other types of volatile memory may be used instead of the RAM 12.

[0017] The ROM 13 stores computer programs executed by the processor 11. The ROM 13 may also store fixed data. The ROM 13 may be, for example, a programmable read-only memory (PROM) or an erasable read-only memory (EPROM). Alternatively, other types of non-volatile memory may be used instead of the ROM 13.

[0018] The storage device 14 stores data that is to be saved long-term by the information processing device 10. The storage device 14 may operate as a temporary storage device for the processor 11. The storage device 14 may include, for example, at least one of a hard disk device, a magneto-optical disk device, an SSD (Solid State Drive), and a disk array device.

[0019] The input device 15 is a device that receives input instructions from a user of the information processing device 10. The input device 15 may include, for example, at least one of a keyboard, a mouse, and a touch panel. The input device 15 may be configured as a mobile terminal such as a smartphone or a tablet. The input device 15 may also be, for example, a device that includes a microphone and is capable of voice input.

[0020] The output device 16 is a device that outputs information related to the information processing device 10 to the outside. For example, the output device 16 may be a display device (e.g., a display) that can display information related to the information processing device 10. The output device 16 may also be a speaker or the like that can output information related to the information processing device 10 as audio. The output device 16 may be configured as a mobile terminal such as a smartphone or a tablet. The output device 16 may also be a device that outputs information in a format other than an image. For example, the output device 16 may be a speaker that outputs information related to the information processing device 10 as audio.

[0021] 1 shows an example of an information processing device 10 including multiple devices, but all or some of the functions may be realized by a single device. Such an information processing device may be configured to include only the above-mentioned processor 11, RAM 12, and ROM 13, and the other components (i.e., the storage device 14, input device 15, output device 16, etc.) may be provided by an external device connected to the information processing device 10. Furthermore, some of the calculation functions of the information processing device 10 may be realized by an external device (e.g., an external server, a cloud, etc.).

[0022] (Functional Configuration) Next, the functional configuration of the information processing device 10 according to the first embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing the functional configuration of the information processing device according to the first embodiment.

[0023] 2, the information processing device 10 according to the first embodiment is a device that performs class classification of input sequence data, and is configured to include, as components for realizing its functions, a data acquisition unit 50, a likelihood ratio calculation unit 100, and a class classification unit 200. Each of the data acquisition unit 50, the likelihood ratio calculation unit 100, and the class classification unit 200 may be a processing block realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0024] The data acquisition unit 50 is configured to acquire multiple elements included in the sequence data. The data acquisition unit 50 may acquire data directly from any data acquisition device (e.g., a camera, a microphone, etc.), or may read data previously acquired by a data acquisition device and stored in storage, etc. When acquiring data from a camera, the data acquisition unit 50 may be configured to acquire data from each of multiple cameras. The elements of the sequence data acquired by the data acquisition unit 50 are configured to be output to the likelihood ratio calculation unit 100. Note that sequence data is data including multiple elements arranged in a predetermined order, and an example of this is time-series data. More specific examples of sequence data include, but are not limited to, video data, audio data, or subdivided image data.

[0025] The likelihood ratio calculation unit 100 is configured to be able to calculate a likelihood ratio based on at least two consecutive elements among the multiple elements acquired by the data acquisition unit 50. Note that the "likelihood ratio" here is an index indicating the likelihood of the class to which the sequence data belongs. Specific examples of likelihood ratios and specific calculation methods will be described in detail in other embodiments below. The likelihood ratio calculation unit 100 according to this embodiment is also configured to be able to calculate the likelihood ratio using an activation function. This activation function will be described in detail later.

[0026] The classification unit 200 is configured to classify sequential data based on the likelihood ratio calculated by the likelihood ratio calculation unit 100. The classification unit 200 selects at least one class to which the sequential data belongs from among multiple candidate classes. The candidate classes may be preset. Alternatively, the candidate classes may be appropriately set by a user or appropriately set based on the type of sequential data being handled. For example, the multiple classes may be set as a class indicating that a face included in video data is a real face (i.e., a biological face) and a class indicating that a face is a fake face (e.g., a face in a photograph or a 3D mask). In this way, the information processing device can be used as an impersonation detection device. Note that the number of candidate classes is not limited to two and may be three or more classes.

[0027] The information processing device 10 may be configured with a learning unit (not shown). Specifically, the information processing device 10 may be configured to have a function of performing learning related to likelihood ratio calculation. The information processing device 10 learns by, for example, inputting training data prepared in advance. This training data may be configured as a set of, for example, sequence data and information on the correct class to which the sequence data belongs (i.e., correct data). When training the information processing device 10, each parameter of the information processing device 10 may be optimized, for example, so that the loss function calculated by inputting the training data is reduced.

[0028] (Characteristics of Activation Function) Next, the characteristics of the activation function used in the information processing device 10 according to the first embodiment (specifically, the activation function used by the likelihood ratio calculation unit 100) will be described.

[0029] As already explained, the likelihood ratio calculation unit 100 according to this embodiment is configured to be able to calculate likelihood ratios using an activation function. The activation function according to this embodiment has at least the following three characteristics:

[0030] The first feature is that the value range is wider than [-1, 1]. For example, the tanh function and sigmoid function, which are sometimes used as general activation functions, have a value range of [-1, 1], but the activation function according to this embodiment has a wider value range than these functions. Therefore, the activation function according to this embodiment has higher expressive power than functions with a narrower value range. The value range of the activation function according to this embodiment may be, for example, [-∞, ∞].

[0031] The second feature is that the output value changes more slowly than the input value. For example, if the input value is x and the output value is y, the slope of the activation function according to this embodiment is gentler than that of y = x. Therefore, the activation function according to this embodiment is less likely to diverge even when the input value becomes large.

[0032] The third feature is that the gradient at the origin does not diverge. That is, the activation function according to this embodiment is designed so that the value does not diverge when the input is set to 0 after differentiation.

[0033] (Operational Flow) Next, the operational flow of the information processing device 10 according to the first embodiment will be described with reference to Fig. 3. Fig. 3 is a flowchart showing the operational flow of the information processing device according to the first embodiment.

[0034] 3, when the information processing device 10 starts operating, the data acquiring unit 50 first acquires elements included in the sequence data (step S11). The data acquiring unit 50 outputs the acquired elements of the sequence data to the likelihood ratio calculating unit 100. The likelihood ratio calculating unit 100 then calculates a likelihood ratio based on two or more acquired elements (step S12). At this time, the likelihood ratio calculating unit 100 calculates the likelihood ratio using an activation function having the above-mentioned characteristics.

[0035] Next, the classification unit 200 performs classification based on the calculated likelihood ratio (step S13). Classification may determine one class to which the sequence data belongs, or may determine multiple classes to which the sequence data is likely to belong. The classification unit 200 may have a function to output the classification result. For example, the classification unit 200 may output the classification result to a display or the like. Alternatively, the classification unit 200 may output the classification result as sound via a speaker or the like.

[0036] If the calculated likelihood ratio does not exceed a predetermined threshold (i.e., a threshold for determining which class to classify), the classification unit 200 may calculate the likelihood ratio again without performing classification (i.e., without determining which class to classify into). In this case, the data acquisition unit 50 may acquire new elements included in the sequence data, and a new likelihood ratio may be calculated.

[0037] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the first embodiment will be described with reference to Fig. 4. Fig. 4 is a graph showing an example of a likelihood ratio calculated by the information processing device according to the first embodiment, together with a comparative example.

[0038] In Figure 4, it is preferable that the likelihood ratio used for class classification gradually changes in a predetermined direction as the number of samples (i.e., input elements) increases. However, in a comparative example using an activation function different from that of this embodiment, the likelihood ratio reaches a plateau (i.e., the likelihood ratio stops changing) even as the number of samples increases. One cause of the likelihood ratio reaching a plateau is, for example, a narrow threshold value for the activation function. While this type of plateau in the likelihood ratio does not occur in all cases, if it does occur, there is a risk that appropriate class classification will not be possible.

[0039] One possible measure to prevent the likelihood ratio from reaching a plateau is to not use an activation function. However, since the activation function contributes to stable learning, not using an activation function may result in unstable learning.

[0040] However, in the information processing device 10 according to the first embodiment, likelihood ratios are calculated using an activation function whose range is wider than [-1, 1], whose output values ​​change more gradually than input values, and whose gradient at the origin does not diverge. In this way, likelihood ratios can be calculated while suppressing the aforementioned plateauing by taking advantage of the high expressive power provided by the wide range of the activation function. That is, likelihood ratios can be calculated with high accuracy for various series of data. Furthermore, the use of an activation function also enables stable learning. That is, the information processing device 10 according to the first embodiment can achieve both highly accurate likelihood ratio estimation and stable learning.

[0041] Second Embodiment An information processing device 10 according to a second embodiment will be described with reference to Fig. 5. Note that the second embodiment describes an example of the activation function described above, and the device configuration and operational flow may be the same as those of the first embodiment. Therefore, the following will describe in detail the differences from the first embodiment, and will omit a description of other overlapping parts as appropriate.

[0042] (Specific Example of Activation Function) First, a specific example of an activation function used in the information processing device 10 according to the second embodiment will be described with reference to Fig. 5. Fig. 5 is a graph showing an example of an activation function used in the information processing device according to the second embodiment.

[0043] In FIG. 5, the information processing device 10 according to the second embodiment uses an activation function that combines square root functions so as to be point-symmetric with respect to the origin. Hereinafter, this activation function will be referred to as a back-to-back-square-root function (B2Bsqrt function). The B2Bsqrt function satisfies the three characteristics already explained (i.e., the range is wider than [-1, 1], the change in output value is more gradual than the change in input value, and the gradient at the origin does not diverge). As an example of the B2Bsqrt function, for example, the function f shown in the following formula (1) is used. １ Examples include:

[0044]

[0045] Here, "x" is an input value, and "α" is a predetermined coefficient (hyperparameter). As shown in FIG. 5, the shape of the function changes by changing the value of α. The B2Bsqrt function in the above formula (1) is merely an example, and can be modified as needed as long as it satisfies the three characteristics required for the activation function according to this embodiment.

[0046] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the second embodiment will be described.

[0047] In the information processing device 10 according to the second embodiment, a B2Bsqrt function, which is a combination of a square root function, is used as the activation function. This B2Bsqrt function has the following characteristics: its range is wider than [-1, 1], its output value changes more slowly than its input value, and its gradient at the origin does not diverge. Therefore, as explained in the first embodiment, it is possible to achieve both highly accurate likelihood ratio estimation and stable learning.

[0048] Third Embodiment An information processing device 10 according to a third embodiment will be described with reference to Fig. 6. Similar to the second embodiment, the third embodiment describes an example of an activation function, and the device configuration and operational flow may be similar to those of the first embodiment. Therefore, the following will describe in detail only the differences from the previously described embodiments, and will omit a description of other overlapping parts as appropriate.

[0049] (Specific Example of Activation Function) First, a specific example of the activation function used in the information processing device 10 according to the third embodiment will be described with reference to Fig. 6. Fig. 6 is a graph showing an example of the activation function used in the information processing device according to the third embodiment.

[0050] As shown in Fig. 6, the information processing device 10 according to the third embodiment uses an activation function that combines log functions so as to be point-symmetric with respect to the origin. Hereinafter, this activation function will be referred to as a logistic-activation function. The logistic-activation function satisfies the three characteristics already explained (i.e., the range is wider than [-1, 1], the change in the output value is more gradual than the change in the input value, and the gradient at the origin does not diverge). As an example of the logistic-activation function, for example, the function f shown in the following formula (2) is used. １ Examples include:

[0051]

[0052] Here, "x" is an input value, and "α" is a predetermined coefficient (hyperparameter). The logistic-activation function of the above formula (2) is merely an example, and can be modified as appropriate as long as it satisfies the three characteristics required for the activation function according to this embodiment.

[0053] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the third embodiment will be described.

[0054] In the information processing device 10 according to the third embodiment, a logistic-activation function combining a log function is used as the activation function. This logistic-activation function has the characteristics that its range is wider than [-1, 1], the output value changes more slowly than the input value, and the gradient at the origin does not diverge. Therefore, as explained in the first embodiment, it is possible to achieve both highly accurate likelihood ratio estimation and stable learning.

[0055] <Fourth embodiment> An information processing device 10 according to a fourth embodiment will be described with reference to Figures 7 and 8. Note that the fourth embodiment differs only in part of the configuration and operation from the first to third embodiments described above, and other parts may be similar to the first to third embodiments. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit a description of other overlapping parts as appropriate.

[0056] (Functional Configuration) First, the functional configuration of the information processing device 10 according to the fourth embodiment will be described with reference to Fig. 7. Fig. 7 is a block diagram showing the functional configuration of the information processing device according to the fourth embodiment. Note that in Fig. 7, the same elements as those shown in Fig. 2 are denoted by the same reference numerals.

[0057] 7, the information processing device 10 according to the fourth embodiment is configured to include, as components for realizing its functions, a data acquisition unit 50, a likelihood ratio calculation unit 100, and a class classification unit 200. In particular, in the fourth embodiment, the likelihood ratio calculation unit 100 includes a first calculation unit 110 and a second calculation unit 120. Note that each of the first calculation unit 110 and the second calculation unit 120 may be realized by, for example, the above-mentioned processor 11 (see FIG. 1).

[0058] The first calculation unit 110 is configured to be able to calculate an individual likelihood ratio based on two consecutive elements included in the sequence data. The individual likelihood ratio is calculated as a likelihood ratio indicating the likelihood of a class to which the two consecutive elements belong. The first calculation unit 110 may, for example, sequentially acquire elements included in the sequence data from the data acquisition unit 50 and sequentially calculate individual likelihood ratios based on the two consecutive elements. The individual likelihood ratios calculated by the first calculation unit 110 are configured to be output to the second calculation unit 120.

[0059] The second calculation unit 120 is configured to calculate an integrated likelihood ratio based on the multiple individual likelihood ratios calculated by the first calculation unit 110. The integrated likelihood ratio is calculated as a likelihood ratio indicating the likelihood of a class to which multiple elements considered in each of the multiple individual likelihood ratios belong. In other words, the integrated likelihood ratio is calculated as a likelihood ratio indicating the likelihood of a class to which sequence data containing multiple elements belongs. The integrated likelihood ratio calculated by the second calculation unit 120 is output to the classification unit 200. The classification unit 200 classifies the sequence data based on the integrated likelihood ratio.

[0060] (Flow of Operation) Next, the flow of operation of the information processing device 10 according to the fourth embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing the flow of operation of the information processing device according to the fourth embodiment.

[0061] 8 , when the information processing device 10 according to the fourth embodiment starts operating, the data acquisition unit 50 first acquires elements included in the sequence data (step S21). The data acquisition unit 50 outputs the acquired elements of the sequence data to the first calculation unit 110.

[0062] The first calculation unit 110 then calculates an individual likelihood ratio based on the two consecutive elements obtained (step S22). Thereafter, the second calculation unit 120 calculates an integrated likelihood ratio based on the multiple individual likelihood ratios calculated by the first calculation unit 110 (step S23).

[0063] Next, the classification unit 200 performs classification based on the calculated integrated likelihood ratio (step S24). The classification may determine a single class to which the sequence data belongs, or may determine multiple classes to which the sequence data is likely to belong.

[0064] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the fourth embodiment will be described.

[0065] As described with reference to Figures 7 and 8, the information processing device 10 according to the fourth embodiment first calculates individual likelihood ratios based on two elements, and then calculates an integrated likelihood ratio based on multiple individual likelihood ratios. Using the integrated likelihood ratio calculated in this manner, it becomes possible to appropriately select the class to which the sequence data belongs. Furthermore, the information processing device 10 according to the fourth embodiment calculates each likelihood ratio using the activation function described above, thereby achieving both highly accurate likelihood ratio estimation and stable learning.

[0066] Fifth Embodiment An information processing device 10 according to a fifth embodiment will be described with reference to Figures 9 and 10. The fifth embodiment differs from the fourth embodiment described above only in some configurations and operations, and other parts may be the same as the fourth embodiment. Therefore, the following will describe in detail the parts that differ from the embodiments already described, and will omit explanations of other overlapping parts as appropriate.

[0067] (Functional Configuration) First, the functional configuration of the information processing device 10 according to the fifth embodiment will be described with reference to Fig. 9. Fig. 9 is a block diagram showing the functional configuration of the information processing device according to the fifth embodiment. Note that in Fig. 9, the same elements as those shown in Figs. 2 and 7 are denoted by the same reference numerals.

[0068] As shown in FIG. 9 , the information processing device 10 according to the fifth embodiment includes a data acquisition unit 50, a likelihood ratio calculation unit 100, and a classification unit 200 as components for implementing its functions. The likelihood ratio calculation unit 100 includes a first calculation unit 110 and a second calculation unit 120, similar to the fourth embodiment. In the fifth embodiment, the first calculation unit 110 includes an individual likelihood ratio calculation unit 111 and a first storage unit. The second calculation unit 120 includes an integrated likelihood ratio calculation unit 121 and a second storage unit 122. Each of the individual likelihood ratio calculation unit 111 and the integrated likelihood ratio calculation unit 121 may be a processing block implemented by, for example, the processor 11 (see FIG. 1 ). Each of the first storage unit 112 and the second storage unit 122 may be implemented by, for example, the storage device 14 (see FIG. 1 ).

[0069] The individual likelihood ratio calculation unit 111 is configured to calculate an individual likelihood ratio based on two consecutive elements among the elements sequentially acquired by the data acquisition unit 50. More specifically, the individual likelihood ratio calculation unit 111 calculates an individual likelihood ratio based on a newly acquired element and past data stored in the first storage unit 112. The information stored in the first storage unit 112 is configured to be readable by the individual likelihood ratio calculation unit 111. When the first storage unit 112 stores past individual likelihood ratios, the individual likelihood ratio calculation unit 111 may read the stored past individual likelihood ratios and calculate new individual likelihood ratios that take the acquired elements into consideration. On the other hand, when the first storage unit 112 stores the elements acquired in the past, the individual likelihood ratio calculation unit 111 may calculate past individual likelihood ratios from the stored past elements and calculate a likelihood ratio for the newly acquired element.

[0070] The integrated likelihood ratio calculation unit 121 is configured to be able to calculate an integrated likelihood ratio based on a plurality of individual likelihood ratios. The integrated likelihood ratio calculation unit 121 calculates a new integrated likelihood ratio using the individual likelihood ratios calculated by the individual likelihood ratio calculation unit 111 and past integrated likelihood ratios stored in the second storage unit 122. The information stored in the second storage unit 122 (i.e., past integrated likelihood ratios) is configured to be readable by the integrated likelihood ratio calculation unit 121.

[0071] (Likelihood Ratio Calculation Operation) Next, the flow of the likelihood ratio calculation operation (i.e., the operation when the likelihood ratio calculation unit 100 calculates the likelihood ratio) in the information processing device 10 according to the seventh embodiment will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the flow of the likelihood ratio calculation operation in the information processing device according to the fifth embodiment.

[0072] 10 , when the likelihood ratio calculation operation according to the fifth embodiment is started, the individual likelihood ratio calculation unit 111 in the first calculation unit 110 first reads past data from the first storage unit 112 (step S31). The past data may be, for example, the processing result by the individual likelihood ratio calculation unit 111 of the element acquired immediately before the element currently acquired by the data acquisition unit 50 (in other words, the individual likelihood ratio calculated for the immediately previous element). Alternatively, the past data may be the element itself acquired immediately before the element currently acquired.

[0073] Next, the individual likelihood ratio calculation unit 111 calculates a new individual likelihood ratio (i.e., an individual likelihood ratio for the element currently acquired by the data acquisition unit 50) based on the element acquired by the data acquisition unit 50 and the past data read from the first storage unit 112 (step S32). The individual likelihood ratio calculation unit 111 outputs the calculated individual likelihood ratio to the second calculation unit 120. The individual likelihood ratio calculation unit 111 may store the calculated individual likelihood ratio in the first storage unit 112.

[0074] Next, the integrated likelihood ratio calculation unit 121 in the second calculation unit 120 reads out a past integrated likelihood ratio from the second storage unit 122 (step S33). The past integrated likelihood ratio may be, for example, the processing result by the integrated likelihood ratio calculation unit 121 for the element acquired immediately before the element currently acquired by the data acquisition unit 50 (in other words, the integrated likelihood ratio calculated for the immediately previous element).

[0075] Next, the integrated likelihood ratio calculation unit 121 calculates a new integrated likelihood ratio (i.e., an integrated likelihood ratio for the element currently acquired by the data acquisition unit 50) based on the likelihood ratio calculated by the individual likelihood ratio calculation unit 111 and the past integrated likelihood ratio read from the second storage unit 122 (step S34). The integrated likelihood ratio calculation unit 121 outputs the calculated integrated likelihood ratio to the classifying unit 200. The integrated likelihood ratio calculation unit 121 may store the calculated integrated likelihood ratio in the second storage unit 122.

[0076] (Technical Effects) Next, technical effects obtained by the information processing device 10 according to the fifth embodiment will be described.

[0077] 9 and 10 , in the information processing device 10 according to the sixth embodiment, individual likelihood ratios are calculated using past individual likelihood ratios, and then an integrated likelihood ratio is calculated using past integrated likelihood ratios. Using the integrated likelihood ratio calculated in this manner makes it possible to appropriately select the class to which the sequence data belongs. Furthermore, in the information processing device 10 according to the fifth embodiment, each likelihood ratio is calculated using the activation function described above, so that both highly accurate likelihood ratio estimation and stable learning can be achieved.

[0078] The scope of each embodiment also includes a processing method in which a program that operates the configuration of each embodiment to realize the functions of the above-described embodiments is recorded on a recording medium, the program recorded on the recording medium is read as code, and the program is executed on a computer. In other words, a computer-readable recording medium is also included in the scope of each embodiment. Furthermore, each embodiment includes not only a recording medium on which the above-described program is recorded, but also the program itself.

[0079] Examples of recording media that can be used include floppy disks, hard disks, optical disks, magneto-optical disks, CD-ROMs, magnetic tapes, non-volatile memory cards, and ROMs. Furthermore, the scope of each embodiment is not limited to programs that execute processes by themselves, but also includes programs that execute processes by operating on an OS in conjunction with other software or expansion board functions. Furthermore, the program itself may be stored on a server, and part or all of the program may be downloadable from the server to a user terminal. The program may be provided to the user in, for example, a SaaS (Software as a Service) format.

[0080] <Supplementary Notes> The above-described embodiment may be further described as in the following supplementary notes, but is not limited to the following.

[0081] (Supplementary Note 1) The information processing device described in Supplementary Note 1 is an information processing device including: an acquisition means for acquiring a plurality of elements included in sequence data; a calculation means for calculating, from at least two consecutive elements among the plurality of elements, a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge; and a classification means for classifying the sequence data into at least one class among a plurality of candidate classes based on the likelihood ratio.

[0082] (Supplementary Note 2) The information processing device according to Supplementary Note 2 is the information processing device according to Supplementary Note 1, wherein the activation function is a function obtained by combining square root functions so as to be point-symmetric with respect to the origin.

[0083] (Supplementary Note 3) In the information processing device according to Supplementary Note 3, the activation function is f=sign(x){(α+|x|) １／２ -α １／２} (x: input value, α: predetermined coefficient).

[0084] (Supplementary Note 4) The information processing device according to Supplementary Note 4 is the information processing device according to Supplementary Note 1, wherein the activation function is a function obtained by combining log functions so as to be point-symmetric with respect to the origin.

[0085] (Supplementary Note 5) The information processing device according to Supplementary Note 5 is the information processing device according to Supplementary Note 4, in which the activation function includes f = sign(x) {log(α + |x|)} (x: input value, α: predetermined coefficient).

[0086] (Supplementary Note 6) The information processing method described in Supplementary Note 6 is an information processing method that, by at least one computer, acquires a plurality of elements included in sequence data, calculates a likelihood ratio indicating the likelihood of a class to which the sequence data belongs from at least two consecutive elements among the plurality of elements using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge, and classifies the sequence data into at least one class among a plurality of candidate classes based on the likelihood ratio.

[0087] (Supplementary Note 7) The recording medium described in Supplementary Note 7 is a recording medium having recorded thereon a computer program for causing at least one computer to execute an information processing method, which includes acquiring a plurality of elements included in sequence data, calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs from at least two consecutive elements among the plurality of elements using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than that of the input value, and whose gradient at the origin does not diverge, and classifying the sequence data into at least one class among a plurality of candidate classes based on the likelihood ratio.

[0088] (Supplementary Note 8) The computer program described in Supplementary Note 8 causes at least one computer to execute an information processing method, which includes acquiring a plurality of elements included in sequence data, calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs from at least two consecutive elements among the plurality of elements using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge, and classifying the sequence data into at least one class among a plurality of candidate classes based on the likelihood ratio.

[0089] (Supplementary Note 9) The information processing system described in Supplementary Note 9 is an information processing system including: an acquisition means for acquiring a plurality of elements included in sequence data; a calculation means for calculating, from at least two consecutive elements among the plurality of elements, a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge; and a classification means for classifying the sequence data into at least one class among a plurality of candidate classes based on the likelihood ratio.

[0090] This disclosure may be modified as appropriate within the scope that does not contradict the gist or idea of ​​the invention that can be read from the claims and the entire specification, and information processing devices, information processing methods, and recording media that involve such modifications are also included in the technical idea of ​​this disclosure.

[0091] REFERENCE SIGNS LIST 10 Information processing device 50 Data acquisition unit 100 Likelihood ratio calculation unit 110 First calculation unit 111 Individual likelihood ratio calculation unit 112 First storage unit 120 Second calculation unit 121 Integrated likelihood ratio calculation unit 122 Second storage unit 200 Classification unit

Claims

1. An acquisition means for acquiring a plurality of elements included in the sequence data; a calculation means for calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, from at least two consecutive elements among the plurality of elements, using an activation function whose range is wider than [-1, 1], whose output value changes more gradually than whose input value changes, and whose gradient at the origin does not diverge; a classification means for classifying the sequence data into at least one class out of a plurality of classes that are classification candidates based on the likelihood ratio; An information processing device comprising:

2. The activation function is a function obtained by combining square root functions so as to be point-symmetric with respect to the origin. The information processing device according to claim 1 .

3. The activation function is f=sign(x){(α+|x|) １／２ -α １／２ } (x: input value, α: predetermined coefficient), The information processing device according to claim 2 .

4. The activation function is a function obtained by combining log functions so as to be point-symmetric with respect to the origin. The information processing device according to claim 1 .

5. The activation function is f=sign(x) {log(α+|x|)} (x: input value, α: predetermined coefficient), The information processing device according to claim 4.

6. by at least one computer, Obtain multiple elements contained in the sequence data, calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, using an activation function whose range is wider than [-1, 1], whose output value changes more slowly than whose input value changes, and whose gradient at the origin does not diverge, from at least two consecutive elements among the plurality of elements; classifying the sequence data into at least one class out of a plurality of classes that are classification candidates based on the likelihood ratio; Information processing methods.

7. At least one computer Obtain multiple elements contained in the sequence data, calculating a likelihood ratio indicating the likelihood of a class to which the sequence data belongs, using an activation function whose range is wider than [-1, 1], whose output value changes more slowly than whose input value changes, and whose gradient at the origin does not diverge, from at least two consecutive elements among the plurality of elements; classifying the sequence data into at least one class out of a plurality of classes that are classification candidates based on the likelihood ratio; A computer program for executing an information processing method.