Inference apparatus

Abstract

To provide a novel method for determining a non-equilibrium Green function for a physical system consisting of many bodies.SOLUTION: An inference apparatus according to an embodiment comprises at least one memory and at least one processor. At least one processor calculates an initial Hamiltonian for material based on a neural network algorithm, and calculates a non-equilibrium Green function for the material based on the initial Hamiltonian.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] TECHNICAL FIELD An embodiment of the present disclosure relates to an inference device. [Background technology]

[0002] For example, when calculating the non-equilibrium Green's function of a physical system consisting of many atomic nuclei and electrons, the Hamiltonian of the physical system is required. However, since the Hamiltonian of such a physical system cannot be obtained by exact calculation, it is generally obtained by an approximate calculation.

[0003] For example, a method using a density functional theory (DFT) model as an approximate calculation method (DFT method) can calculate a Hamiltonian with high accuracy. Also, a method using a semi-empirical model as an approximate calculation method (semi-empirical method) can calculate a Hamiltonian with a small calculation load. [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Fabian Ducry, Jan Aeschlimann, Mathieu Luisier, “Electro-thermal transport in disordered nanostructures: a modeling perspective” Nanoscale Advances, Published 19 May 2020 [Non-Patent Document 2] https: / / docs.quantumatk.com / manual / Types / DeviceSemiEmpiricalCalculator / DeviceSemiEmpiricalCalculator.html#devicesemiempiricalcalculator-c [Non-Patent Document 3] He Li, Zun Wang, Nianlong Zou, Meng Ye, Runzhang Xu, Xiaoxun Gong, Wenhui Duan, Yong Xu “Deep-learning density functional theory Hamiltonian for efficient ab initio electronic-structure calculation,” Nature Computational Science volume 2, pages 367-377 (2022) Summary of the Invention [Problem to be solved by the invention]

[0005] However, when the DFT method is used to obtain the Hamiltonian and non-equilibrium Green's functions of a physical system, the computational load is large. On the other hand, when the semi-empirical method is used to obtain the Hamiltonian and non-equilibrium Green's functions of a physical system, the computational load can be reduced, but the accuracy may not be sufficient.

[0006] The problem to be solved by this disclosure is to provide a new method for determining the non-equilibrium Green's function of a physical system consisting of many nuclei and electrons. [Means for solving the problem]

[0007] An inference device according to an embodiment includes at least one memory and at least one processor, and the at least one processor calculates a Hamiltonian as an initial value for a material based on a neural network algorithm, and calculates a non-equilibrium Green's function for the material based on the Hamiltonian as the initial value. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram showing an example of a hardware configuration of an inference device according to an embodiment. [Diagram 2]FIG. 2 is a diagram illustrating an example of a functional block in a processor according to the embodiment. [Diagram 3] FIG. 3 is a flowchart showing an example of the flow of an inference process executed by the inference device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an inference device according to an embodiment will be described with reference to the drawings. In the following embodiments, parts with the same reference numerals perform the same operation, and duplicated descriptions will be omitted as appropriate. The following embodiments do not limit the disclosed technology. Each embodiment can be appropriately combined as long as the processing contents are not contradictory.

[0010] In the following, for the sake of concrete explanation, a physical system is considered as a many-body problem in which a substance is composed of a large number of atomic nuclei and electrons. In this embodiment, an electron transport calculation using a non-equilibrium Green's function may be performed using the SCF (Self Consistent Field) method, and the potential, electron density, and various physical quantities of the substance may be calculated using the results. In this case, a Hamiltonian (potential) as an initial value used in the electron transport calculation using the non-equilibrium Green's function may be calculated based on a neural network model, which is a machine-learned model.

[0011] Hereinafter, the embodiments will be described in detail with reference to the drawings.

[0012] Fig. 1 is a block diagram showing an example of a hardware configuration of an inference device 1 according to the first embodiment. As shown in Fig. 1, the inference device 1 may be connected to an external device 9A via a communication network 5. The inference device 1 may also include an external device 9B connected via a device interface 39.

[0013] The inference device 1 may input position information (three-dimensional coordinates) of multiple atoms contained in a substance and output a Hamiltonian of the three-dimensional molecular structure of the substance. The substance is not limited to molecules, and may be various crystals, etc.

[0014] The inference device 1 may include a computer 30 and an external device 9B connected to the computer 30 via a device interface 39. The computer 30 may include, for example, a processor 31, a main storage device (memory) 33, an auxiliary storage device (memory) 35, a network interface 37, and a device interface 39. The inference device 1 may be realized as the computer 30 in which the processor 31, the main storage device 33, the auxiliary storage device 35, the network interface 37, and the device interface 39 are connected via a bus 41.

[0015] The computer 30 shown in FIG. 1 includes one of each component, but may include a plurality of the same components. Although one computer 30 is shown in FIG. 1, the software may be installed in a plurality of computers, and each of the plurality of computers may execute the same or different parts of the software. In this case, the computer may be in the form of distributed computing in which each computer communicates via a network interface 37 or the like to execute the processing. That is, the inference device 1 in this embodiment may be configured as a system in which one or more computers execute instructions stored in one or more storage devices to realize various functions described below. Also, the information transmitted from the terminal may be processed by one or more computers provided on the cloud, and the processing results may be transmitted to a terminal such as a display device (display unit) corresponding to the external device 9B.

[0016] Various calculations of the inference device 1 in this embodiment may be executed in parallel using one or more processors, or using multiple computers via a network. Also, various calculations may be distributed to multiple computing cores in a processor and executed in parallel. Also, a part or all of the processes, means, etc. disclosed herein may be executed by at least one of a processor and a storage device provided on a cloud that can communicate with the computer 30 via a network. In this way, various things described later in this embodiment may be in the form of parallel computing by one or more computers.

[0017] The processor 31 may be an electronic circuit (such as a processing circuit, processing circuitry, CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), or ASIC (Application Specific Integrated Circuit)) including a control device and an arithmetic device of the computer 30. The processor 31 may also be a semiconductor device including a dedicated processing circuit. The processor 31 is not limited to an electronic circuit using electronic logic elements, and may be realized by an optical circuit using optical logic elements. The processor 31 may also include an arithmetic function based on quantum computing.

[0018] The processor 31 performs arithmetic processing based on data and software (programs) input from each device, etc., in the internal configuration of the computer 30, and can output the arithmetic results and control signals to each device, etc. The processor 31 may control each component constituting the computer 30 by executing the OS (Operating System) of the computer 30, applications, etc.

[0019] The inference device 1 in this embodiment may be realized by one or more processors 31. Here, the processor 31 may refer to one or more electronic circuits arranged on one chip, or to one or more electronic circuits arranged on two or more chips or two or more devices. When multiple electronic circuits are used, the electronic circuits may communicate with each other by wire or wirelessly.

[0020] The main memory 33 is a memory device that stores instructions executed by the processor 31 and various data, and information stored in the main memory 33 is read by the processor 31. The auxiliary memory 35 is a memory device other than the main memory 33. These memory devices refer to any electronic components capable of storing electronic information, and may be semiconductor memories. The semiconductor memories may be either volatile memories or nonvolatile memories. A memory device for saving various data used in the inference device 3 according to this embodiment may be realized by the main memory 33 or the auxiliary memory 35, or may be realized by an internal memory built into the processor 31. For example, the memory unit in this embodiment may be realized by the main memory 33 or the auxiliary memory 35.

[0021] A plurality of processors may be connected (coupled) to one storage device (memory), or a single processor 31 may be connected. A plurality of storage devices (memories) may be connected (coupled) to one processor. When the inference device 1 in this embodiment is configured with at least one storage device (memory) and a plurality of processors connected (coupled) to this at least one storage device (memory), it may include a configuration in which at least one of the plurality of processors is connected (coupled) to at least one storage device (memory). This configuration may also be realized by storage devices (memories) and processors 31 included in a plurality of computers. Furthermore, it may include a configuration in which the storage device (memory) is integrated with the processor 31 (for example, a cache memory including an L1 cache and an L2 cache).

[0022] The network interface 37 is an interface for connecting to the communication network 5 wirelessly or by wire. The network interface 37 may be an appropriate interface such as one conforming to an existing communication standard. The network interface 37 may exchange information with an external device 9A connected via the communication network 5. The communication network 5 may be any one of a wide area network (WAN), a local area network (LAN), a personal area network (PAN), etc., or a combination thereof, as long as information is exchanged between the computer 30 and the external device 9A. An example of a WAN is the Internet, an example of a LAN is IEEE802.11 or Ethernet (registered trademark), and an example of a PAN is Bluetooth (registered trademark) or Near Field Communication (NFC).

[0023] The device interface 39 is an interface such as a Universal Serial Bus (USB) that directly connects to an output device such as a display device, an input device, and an external device 9 B. The output device may have a speaker that outputs sound and the like.

[0024] The external device 9A is a device connected to the computer 30 via a network. The external device 9B may be a device directly connected to the computer 30.

[0025] The external device 9A or the external device 9B may be, for example, an input device (input unit). The input device is, for example, a device such as a camera, a microphone, a motion capture, various sensors, a keyboard, a mouse, or a touch panel, and provides acquired information to the computer 30. The external device 9A or the external device 9B may also be a device equipped with an input unit, a memory, and a processor, such as a personal computer, a tablet terminal, or a smartphone.

[0026] Moreover, the external device 9A or the external device 9B may be, for example, an output device (output unit). The output device may be, for example, a display device (display unit) such as an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube), a PDP (Plasma Display Panel), or an organic EL (Electro Luminescence) panel, or may be a speaker that outputs sound or the like. The external device 9A or the external device 9B may be a device having an output device, a memory, and a processor, such as a personal computer, a tablet terminal, or a smartphone.

[0027] Furthermore, the external device 9A or the external device 9B may be a storage device (memory). For example, the external device 9A may be a network storage or the like, and the external device 9B may be a storage device such as an HDD.

[0028] Furthermore, the external device 9A or the external device 9B may be a device having some of the functions of the components of the inference device 1 in this embodiment. In other words, the computer 30 may transmit or receive some or all of the processing results of the external device 9A or the external device 9B.

[0029] 2 is a diagram showing an example of a functional block in the processor 31. The processor 31 may include, for example, an acquisition unit 310, a Hamiltonian calculation unit 312, a Green's function calculation unit 314, an electron density calculation unit 315, a physical quantity calculation unit 316, and an output unit 318 as functions realized by the processor 31. The functions realized by the acquisition unit 310, the Hamiltonian calculation unit 312, the Green's function calculation unit 314, the electron density calculation unit 315, the physical quantity calculation unit 316, and the output unit 318 may be stored as programs in, for example, the main storage device 33 or the auxiliary storage device 35. The processor 31 can realize the functions related to the acquisition unit 310, the Hamiltonian calculation unit 312, the Green's function calculation unit 314, the electron density calculation unit 315, the physical quantity calculation unit 316, and the output unit 318 by reading and executing the programs stored in the main storage device 33 or the auxiliary storage device 35.

[0030] The acquiring unit 310 may acquire position information (three-dimensional coordinates) of each atom as an initial value for the target substance, for example, based on an input from a user. The position information of each atom as an initial position may be any three-dimensional coordinates. In addition, in this embodiment, an example is taken in which the processor 31 of the inference device 1 realizes the Hamiltonian calculation unit 312, but if the Hamiltonian calculation unit 312 is provided in another device, the acquiring unit 310 may acquire the Hamiltonian as an initial value calculated in the other device.

[0031] The Hamiltonian calculation unit 312 may input the position information of each atom acquired by the acquisition unit 310, and calculate a Hamiltonian as an initial value of the substance from the position information of each atom contained in the substance. The Hamiltonian calculation unit 312 is realized by, for example, a trained model. For example, a neural network model can be adopted as the trained model.

[0032] Furthermore, when the Hamiltonian calculation unit 312 sequentially performs electron transport calculations using non-equilibrium Green's functions using the SCF method, the Hamiltonian calculation unit 312 may calculate a potential difference using the electron density difference calculated by the electron density calculation unit 315 and the Poisson equation, and use this to update the Hamiltonian. Furthermore, when the electron density difference between the latest electron density and the immediately previous electron density is equal to or smaller than a predetermined threshold value in a determination process (described later) in the electron density calculation unit 315, the Hamiltonian calculation unit 312 may estimate the latest Hamiltonian to be the Hamiltonian optimized for the substance.

[0033] The Green's function calculation unit 314 may calculate a non-equilibrium Green's function using the Hamiltonian as an initial value calculated in the Hamiltonian calculation unit 312 or an updated Hamiltonian and an inverse matrix algorithm. In particular, the Green's function calculation unit 314 may calculate an optimized non-equilibrium Green's function based on the optimized Hamiltonian calculated in the Hamiltonian calculation unit 312.

[0034] When the electron density calculation unit 315 sequentially performs electron transport calculations using non-equilibrium Green's functions using the SCF method, the electron density calculation unit 315 may spatially integrate the latest non-equilibrium Green's functions calculated by the Green's function calculation unit 314 to calculate and update the electron density.

[0035] Furthermore, when the electron density calculation unit 315 sequentially performs the electron transport calculation by the non-equilibrium Green's function using the SCF method, the electron density calculation unit 315 may calculate the difference between the latest electron density and the previous electron density. The electron density calculation unit 315 may execute a determination process to determine whether or not the calculated difference in electron density is equal to or smaller than a predetermined threshold value.

[0036] The physical quantity calculation unit 316 may calculate a predetermined physical quantity based on the optimized non-equilibrium Green's function. Here, the predetermined physical quantity may include at least one of the local density of states, transmittance, current, capacitance, charge, and spin distribution of a substance. As a method for calculating these physical quantities, an existing method may be adopted.

[0037] The output unit 318 may output the physical quantities calculated by the physical quantity calculation unit 316 to the main storage device 33 and / or the auxiliary storage device 35. In addition, the output unit 318 can also output the physical quantities calculated by the physical quantity calculation unit 316 to the external device 9A via the communication network 5.

[0038] (Inference processing) Next, an inference process realized by the inference device 1 according to the embodiment will be described. The inference process may be a process for estimating a predetermined physical quantity of a target substance by performing an electron transport calculation using a non-equilibrium Green's function. In this case, the Hamiltonian used as the initial value may be calculated using a neural network model. In addition, the inference process may include a case where the SCF method is not used and a case where the SCF method is used.

[0039] FIG. 3 is a diagram for explaining the concept of the inference process implemented by the inference device 1 according to the embodiment.

[0040] First, the inference process in the case where the SCF method is not used will be described. As shown in FIG. 3, when the position information of each atom is input, the Hamiltonian calculation unit 312 uses a neural network model to calculate the Hamiltonian H1=H NN may be calculated (step S1).

[0041] The Green's function calculation unit 314 calculates the Hamiltonian H1=H NN A non-equilibrium Green's function G1 may be calculated based on the above (step S2).

[0042] The physical quantity calculation unit 316 may calculate a predetermined physical quantity based on the non-equilibrium Green's function G1 calculated by the Green's function calculation unit 314 (step S3).

[0043] The output unit 318 may output the physical quantity calculated by the physical quantity calculation unit 316 (step S4).

[0044] Inference processing in cases where the SCF method is not used does not require electron density and sequential calculation, which significantly reduces the calculation load and greatly speeds up calculation processing.

[0045] Next, the inference process in the case where the SCF method is used will be described. As shown in Fig. 3, the electron density calculation unit 315 spatially integrates the non-equilibrium Green's function G1 calculated by the Green's function calculation unit 314 to calculate the electron density ρ1. The electron density calculation unit 315 may also calculate the difference δρ1 between a predetermined electron density ρ0 and the electron density ρ1 (step S5). Here, the predetermined electron density ρ0 is, for example, calculated using the Hamiltonian H NN Alternatively, the predetermined electron density ρ0 may be obtained by using the same or a different neural network model to calculate the Fermi energy and Hamiltonian H1, calculating a non-equilibrium Green's function based on the calculated Hamiltonian H1, and integrating the calculated non-equilibrium Green's function G1 from minus infinity to the Fermi energy. Furthermore, instead of calculating ρ0, the same or a different neural network model may be used to calculate potentials V0 and H1 as initial values ​​from position information of each atom, calculating a non-equilibrium Green's function G1 based on the calculated H1, calculating the electron density ρ1 by spatially integrating the calculated non-equilibrium Green's function G1, calculating the potential V1 from the calculated electron density ρ1, calculating δV from the calculated potentials V1 and V0, and updating the Hamiltonian from the calculated δV as described below.

[0046] The Hamiltonian calculation unit 312 calculates the potential difference δV(δρ1) using the electron density difference δρ1 and the Poisson equation, and calculates the potential difference δV(δρ1) and the Hamiltonian H1=H NN Using and, we change the Hamiltonian to H2=H1(=H NN )+ΔV(Δρ1) (step S6: that is, when i=1 in the sequential calculation of the SCF method).

[0047] The Green's function calculation unit 314 calculates H2=H1(=H NN ) + ΔV(Δρ1), a non-equilibrium Green's function G2 may be calculated (step S7).

[0048] The electron density calculation unit 315 calculates the electron density ρ2 by spatially integrating the non-equilibrium Green's function G2 calculated by the Green's function calculation unit 314. In addition, the electron density calculation unit 315 may calculate the difference Δρ2 between the electron density ρ2 and the previous electron density ρ1 (step S8).

[0049] The Hamiltonian calculation unit 312 may calculate the potential difference δV(δρ2) using the electron density difference δρ2 and the Poisson equation, and update the Hamiltonian as H3=H2+δV(δρ2) using the potential difference δV(δρ2) and the latest Hamiltonian H2 (step SS6: that is, the case where i⇒i+1 in the sequential calculation of the SCF method).

[0050] Hereafter, δρ i The iterative calculation of the SCF method may be repeatedly performed until becomes equal to or less than a predetermined threshold value.

[0051] The physical quantity calculation unit 316 calculates Δρ i When falls below a certain threshold, the latest Hamiltonian H i The non-equilibrium Green's function G calculated using i A predetermined physical quantity may be calculated based on the above (step S9).

[0052] The output unit 318 may output the physical quantity calculated by the physical quantity calculation unit 316 (step S10).

[0053] As described above, the inference device 1 according to this embodiment may include at least one memory such as the main storage device 33 and the auxiliary storage device 35, and at least one processor such as the processor 31. The processor 31 calculates a Hamiltonian H1=H NNCalculate the initial Hamiltonian H1=H NN The non-equilibrium Green's function G1 for the material may be calculated based on

[0054] The processor 31 may also calculate the electron density of the material based on the non-equilibrium Green's function, update the Hamiltonian as an initial value using a potential difference calculated based on the electron density, and update the non-equilibrium Green's function based on the updated Hamiltonian. The processor 31 may update the electron density based on the updated non-equilibrium Green's function, and thereafter repeatedly execute each update until a difference between the latest electron density and the previous electron density becomes equal to or less than a threshold, and when the difference becomes equal to or less than the threshold, calculate the non-equilibrium Green's function for the material based on the latest Hamiltonian.

[0055] Therefore, for example, when calculating a Hamiltonian as an initial value, it is not necessary to execute calculations using the DFT method, which has a high load. Therefore, compared to the conventional method, it is possible to significantly reduce the calculation load when calculating the potential (Hamiltonian) of a substance or a non-equilibrium Green's function. Furthermore, in electron transport calculations using the SCF method and the non-equilibrium Green's function, it is empirically known that the convergence of the SCF method changes depending on H1 used as the initial value. In this embodiment, a highly accurate Hamiltonian H obtained based on a neural network algorithm is used. NN is used as the initial value. Therefore, the convergence of the SCF method can be improved and the number of iterations in the sequential calculation can be reduced. In addition, since the calculation load can be significantly reduced, it is possible to enlarge the calculation system and handle larger physical systems than before.

[0056] In addition, when a semi-empirical method is used to calculate a Hamiltonian as an initial value, the calculation load is not large, but it is known that the Hamiltonian cannot be expressed correctly if there is a defect or disturbance in the physical system. According to the inference device of this embodiment, it is possible to significantly improve the calculation accuracy with the same calculation load as when a semi-empirical model is used.

[0057] As described above, a new method can be provided for optimizing the structure of a material, which has a relatively light calculation load and high calculation accuracy.

[0058] (Variation 1) The physical systems targeted by the inference device of the embodiment can include materials used in, for example, transistors (FETs, two-dimensional materials), memories (NAND, ReRAM, PCM, DRAM, MRAM), graphene, nanoribbons, nanotubes, cascade lasers, batteries, solar cells, ion batteries, etc.

[0059] (Variation 2) In the above embodiment, the Hamiltonian H calculated based on the neural network algorithm is NN The Hamiltonian was updated by the SCF method and electron transport calculations were performed using nonequilibrium Green's functions. NN and the one-to-one corresponding electron density ρ NN may be obtained by a neural network algorithm, and the Hamiltonian may be updated by the SCF method using this as the initial value, and electron transport calculations may be performed using a non-equilibrium Green's function.

[0060] Generally, the process of calculating a Hamiltonian from electron density has a smaller calculation load than the process of calculating electron density from a Hamiltonian, so the calculation load in the inference process can be further reduced.

[0061] When realizing the technical idea of ​​the embodiment, a Hamiltonian as an initial value for a material may be calculated based on a neural network algorithm, and a non-equilibrium Green's function for the material may be calculated based on the Hamiltonian as the initial value.

[0062] When the technical ideas in the embodiments are realized by a determination program, the determination program may cause a computer to calculate a Hamiltonian as an initial value for a material based on a neural network algorithm, and to calculate a non-equilibrium Green's function for the material based on the Hamiltonian as the initial value.

[0063] For example, the inference processing according to the embodiment can be realized by installing the determination program in a computer in various analysis devices or analysis servers that analyze non-equilibrium Green's functions of atomic structures composed of multiple atoms, and developing the program in memory. In this case, the program that can cause the computer to execute the method can be stored in a storage medium such as a magnetic disk (hard disk, etc.), an optical disk (CD-ROM, DVD, etc.), or a semiconductor memory and distributed. The procedure and effect of the optimal parameter determination processing by the determination program are the same as those of the embodiment, so a description thereof will be omitted.

[0064] A part or all of each device in the above-mentioned embodiment may be configured with hardware, or may be configured with information processing of software (programs) executed by a CPU, a GPU, or the like. In the case of being configured with information processing of software, software for realizing at least a part of the functions of each device in the above-mentioned embodiment may be stored in a non-transient storage medium (non-transient computer-readable medium) such as a flexible disk, a CD-ROM (Compact Disc-Read Only Memory), or a USB memory, and the software information processing may be executed by reading the software into the computer 30. The software may also be downloaded via the communication network 5. Furthermore, the software may be implemented in a circuit such as an ASIC or an FPGA, so that the information processing is executed by the hardware.

[0065] There is no limitation on the type of storage medium that stores the software. The storage medium is not limited to removable media such as magnetic disks or optical disks, but may be fixed storage media such as hard disks or memory. The storage medium may be provided inside the computer or outside the computer.

[0066] In this specification (including the claims), when the expression "at least one of a, b, and c" or "at least one of a, b, or c" (including similar expressions) is used, it includes any of a, b, c, ab, ac, bc, or abc. It may also include multiple instances of any element, such as aa, abb, aabbcc, etc. Furthermore, it also includes the addition of elements other than the enumerated elements (a, b, and c), such as having d, as in abcd.

[0067] In this specification (including claims), when expressions such as "data as input / based on / according to / in response to" (including similar expressions) are used, unless otherwise specified, it includes cases where various data itself is used as input, and cases where various data that have been processed in some way (e.g., noise-added, normalized, intermediate representation of various data, etc.) are used as input. In addition, when it is stated that a result is obtained "based on / according to / in response to data," it includes cases where the result is obtained based only on the data, and may also include cases where the result is obtained influenced by other data, factors, conditions, and / or states other than the data. In addition, when it is stated that "data is output," it includes cases where various data itself is used as output, and cases where various data that have been processed in some way (e.g., noise-added, normalized, intermediate representation of various data, etc.) are output, unless otherwise specified.

[0068] In this specification (including the claims), the terms "connected" and "coupled" are intended as open-ended terms including any of direct connection / coupling, indirect connection / coupling, electrically connection / coupling, communicatively connection / coupling, functionally connection / coupling, physically connection / coupling, etc. The terms should be interpreted appropriately depending on the context in which the terms are used, but any connection / coupling form that is not intentionally or naturally excluded should be interpreted as being included in the terms without any restriction.

[0069] In this specification (including the claims), when the expression "A configured to B" is used, it may include that the physical structure of element A has a configuration capable of performing operation B, and that the permanent or temporary setting / configuration of element A is configured / set to actually perform operation B. For example, when element A is a general-purpose processor, it is sufficient that the processor has a hardware configuration capable of performing operation B, and is configured to actually perform operation B by setting a permanent or temporary program (instruction). Also, when element A is a dedicated processor or dedicated arithmetic circuit, it is sufficient that the circuit structure of the processor is implemented to actually perform operation B, regardless of whether control instructions and data are actually attached.

[0070] In this specification (including the claims), terms implying containing or possessing (e.g., "comprising / including" and "having") are intended to be open-ended terms that include the inclusion or possession of things other than the object indicated by the object of the term. When the object of such terms implies no quantity or a singular number (such as an article "a" or "an"), the expression should be construed as not being limited to a specific number.

[0071] In this specification (including the claims), even if expressions such as "one or more" or "at least one" are used in some places and expressions that do not specify a quantity or suggest a singular number (expressions using the articles a or an) are used in other places, the latter expressions are not intended to mean "one." In general, expressions that do not specify a quantity or suggest a singular number (expressions using the articles a or an) should be interpreted as not necessarily being limited to a specific number.

[0072] In this specification, when a particular advantage / result is described as being obtained from a particular configuration of an embodiment, it should be understood that the same effect can also be obtained from one or more other embodiments having the same configuration, unless there is a reason to the contrary. However, it should be understood that the presence or absence of the effect generally depends on various factors, conditions, and / or states, and that the effect is not necessarily obtained by the configuration. The effect is merely obtained by the configuration described in the embodiment when various factors, conditions, and / or states are satisfied, and the effect is not necessarily obtained in the invention according to the claim that specifies the configuration or a similar configuration.

[0073] In this specification (including the claims), when a term such as "maximize" is used, it includes finding a global maximum, finding an approximation of a global maximum, finding a local maximum, and finding an approximation of a local maximum, and should be interpreted appropriately according to the context in which the term is used. It also includes finding approximations of these maxima probabilistically or heuristically. Similarly, when a term such as "minimize" is used, it includes finding a global minimum, finding an approximation of a global minimum, finding a local minimum, and finding an approximation of a local minimum, and should be interpreted appropriately according to the context in which the term is used. It also includes finding approximations of these minima probabilistically or heuristically. Similarly, when a term such as "optimize" is used, it includes finding a global optimum, finding an approximation of a global optimum, finding a local optimum, and finding an approximation of a local optimum, and should be interpreted appropriately according to the context in which the term is used. It also includes finding approximations of these optimums probabilistically or heuristically.

[0074] In this specification (including claims), when a plurality of pieces of hardware perform a predetermined process, each piece of hardware may cooperate to perform the predetermined process, or a portion of the hardware may perform all of the predetermined process. Also, a portion of the hardware may perform a portion of the predetermined process, and another piece of hardware may perform the remainder of the predetermined process. In this specification (including claims), when an expression such as "one or more pieces of hardware perform a first process, and the one or more pieces of hardware perform a second process" is used, the hardware performing the first process and the hardware performing the second process may be the same or different. In other words, it is sufficient that the hardware performing the first process and the hardware performing the second process are included in the one or more pieces of hardware. The hardware may include an electronic circuit or a device including an electronic circuit.

[0075] In this specification (including the claims), when multiple storage devices (memories) store data, each of the multiple storage devices (memories) may store only a portion of the data, or may store the entire data.

[0076] Although the embodiments of the present disclosure have been described in detail above, the present disclosure is not limited to the individual embodiments described above. Various additions, modifications, replacements, and partial deletions are possible within the scope of the conceptual idea and intent of the present invention derived from the contents defined in the claims and their equivalents. For example, in all the above-mentioned embodiments, when numerical values ​​or formulas are used in the explanation, they are shown as examples and are not limited to these. In addition, the order of each operation in the embodiments is shown as an example and is not limited to these. [Explanation of symbols]

[0077] 1 Reasoning device 5. Communication Network 9A external device 9B External device 30 Computers 31 Processors 33 Main memory 35 Auxiliary storage device 37 Network Interface 39 Device Interfaces 41 Bus 310 Acquisition Department 312 Hamiltonian Calculation Section 314 Green's Function Calculation Section 315 Electron density calculation section 316 Physical quantity calculation section 319 Output section

Claims

1. At least one memory; At least one processor; The at least one processor Using a neural network, we calculate the Hamiltonian for the material. calculating a non-equilibrium Green's function for the material based on the Hamiltonian; Reasoning device.

2. The at least one processor calculating a predetermined physical quantity of the material based on the non-equilibrium Green's function; The inference device of claim 1 .

3. The at least one processor Calculating an electron density based on the non-equilibrium Green's function; updating the Hamiltonian using a potential difference calculated based on the electron density; updating the non-equilibrium Green's function based on the updated Hamiltonian; updating the electron density based on the updated non-equilibrium Green's function; repeating each of the updates until a difference between the latest electron density and the immediately previous electron density becomes equal to or less than a threshold, and when the difference becomes equal to or less than the threshold, calculating a non-equilibrium Green's function for the material based on the latest Hamiltonian; The inference device of claim 1 .

4. The at least one processor Calculating a predetermined physical quantity of the material based on the latest non-equilibrium Green's function; 4. The inference device of claim 3.

5. The predetermined physical quantity includes at least one of a local density of states, a transmittance, a current, a capacitance, a charge, and a spin distribution of the material.

5. An inference device according to claim 2 or 4.

6. Calculating the initial value of the electron density by diagonalizing the Hamiltonian, integrating the non-equilibrium Green's function up to the Fermi energy, or using a neural network that is the same as or different from the neural network.

4. The inference device of claim 3.

7. At least one memory; At least one processor; The at least one processor The neural network calculates the electron density of the material. calculating a Hamiltonian for the material based on the electron density; calculating a non-equilibrium Green's function for the material based on the Hamiltonian; Reasoning device.

8. The at least one processor calculating a predetermined physical quantity of the material based on the non-equilibrium Green's function; 8. The inference apparatus of claim 7.

9. The at least one processor updating the electron density based on the non-equilibrium Green's function; updating the Hamiltonian using a potential difference calculated based on the electron density; updating the non-equilibrium Green's function based on the updated Hamiltonian; updating the electron density based on the updated non-equilibrium Green's function; repeating each of the updates until a difference between the latest electron density and the immediately previous electron density becomes equal to or less than a threshold, and when the difference becomes equal to or less than the threshold, calculating a non-equilibrium Green's function for the material based on the latest Hamiltonian; 8. The inference apparatus of claim 7.

10. The at least one processor Calculating a predetermined physical quantity of the material based on the latest non-equilibrium Green's function; 10. The inference apparatus of claim 9.

Images