WO2022260178A1 - 訓練装置、推定装置、訓練方法、推定方法及びプログラム - Google Patents

訓練装置、推定装置、訓練方法、推定方法及びプログラム Download PDF

Info

Publication number
WO2022260178A1
WO2022260178A1 PCT/JP2022/023521 JP2022023521W WO2022260178A1 WO 2022260178 A1 WO2022260178 A1 WO 2022260178A1 JP 2022023521 W JP2022023521 W JP 2022023521W WO 2022260178 A1 WO2022260178 A1 WO 2022260178A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
output
atomic
neural network
network model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2022/023521
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
聡 高本
幾 品川
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Preferred Networks Inc
Original Assignee
Preferred Networks Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Preferred Networks Inc filed Critical Preferred Networks Inc
Priority to JP2023527953A priority Critical patent/JP7403032B2/ja
Publication of WO2022260178A1 publication Critical patent/WO2022260178A1/ja
Priority to US18/533,481 priority patent/US20240105288A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
    • G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
    • G16C20/70—Machine learning, data mining or chemometrics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Definitions

  • Supervised learning is often used in optimizing this model.
  • the results of first-principles calculations that have already been obtained, for example, information obtained from databases published on the web can be used.
  • quantum operations such as first-principles calculations are realized by approximate calculations based on respective methods and parameters, the results differ depending on the method used, the parameters used in the method, and the like.
  • training data containing data such as energy for the same atomic structure or atomic structures belonging to the same environment for different label information By using training data having the same atomic structure and the like in this way, the above linear or non-linear relationship is reflected in training. As a result, even if there is no atomic structure in a similar environment with respect to the label information, if similar atomic structure data exists in other label information as training data, appropriate inference processing can be performed. can be executed.
  • the training device 2 trains the model NN on the relationship between the first and second conditions.
  • the relationship between the first and second conditions is incorporated into the model NN.
  • the training device 2 inputs the data on the second atomic structure and the second label information including the second condition to the model NN, outputs the second result and the second condition on the second atomic structure ( Calculate a second error of the second simulation result, approximated in a second software (some parameter in the second algorithm may be used), and use this second error to train the model NN.
  • the training device 2 can optimize the model NN with improved generalization performance.
  • the training unit 204 updates the parameters of the model NN based on the error (S208).
  • the training unit 204 updates the parameters of the model NN based on the gradient, for example, by error backpropagation.
  • the label information in this embodiment may include at least information on any one of various calculation conditions, calculation methods (calculation algorithms), software used for calculation, or various parameters in the software in the atomic simulation.
  • the first condition and the second condition of the atomic simulation at least one of the label information described above may be a different condition.
  • first-principles calculation is shown as an example of atomic simulation, but simulation results may be obtained using other methods. Atom simulation may be performed using a semi-empirical molecular orbital method, a fragment molecular orbital method, or the like, and a simulation result may be obtained.
  • a model capable of appropriately obtaining potential information of the atomic structure based on the label information is generated and inference using this model is realized. be able to.
  • the accuracy may differ depending on the calculation conditions.
  • the training and inference according to this embodiment it is possible to specify a calculation method and perform training and inference regardless of the domain. Therefore, according to the NNP using the model according to this embodiment, it is possible to obtain results under appropriate calculation conditions in appropriate domains. Furthermore, even if the domain is not appropriate (highly accurate) for the calculation conditions, training can be performed to correct the difference between the calculation conditions and other calculation conditions. Therefore, by applying the training and inference according to the present embodiment to a model used in NNP, it becomes possible to appropriately infer potential information of atomic structures belonging to various domains under various calculation conditions.
  • Label information may be set, for example, by defining modes similar to those defined in the previous embodiment. With such a form, expansion becomes easier than other forms when increasing label information and retraining an already existing trained model.
  • the training device 2 may define encoders with granularity such as for each label information, for example, for each software or each mode.
  • the training unit 204 designates an encoder for inputting the atomic structure based on the label information, and inputs the atomic structure to the designated encoder. Then, the output from this encoder is input to the model NN, and training of the model NN is executed in the same manner as in the above-described embodiments. In this embodiment, along with training the model NN, the encoder is also trained. That is, the training unit 204 updates the parameters up to the input layer by error backpropagation based on the output of the model NN, and continues to update the encoder parameters using the gradient information backpropagated to this input layer. In this way, training is repeated.
  • the inference unit 104 infers potential information by inputting this intermediate representation to the model NN and forward propagating it.
  • This reasoning makes it possible to obtain potential information from the atomic structure as an operation result appropriately based on the label information, because the intermediate representation considering the label information can be obtained in the previous encoder.
  • the plurality of encoders and the model NN input information about the first atomic structure to the encoder (first neural network model) determined based on the first label information, and input this output to the model NN.
  • the model NN Taking the first output, inputting information about the second atomic structure into an encoder (second neural network model) that is determined based on the second label information, inputting this output into the model NN to generate the second output It is trained to obtain and used in the estimator 1.
  • All of the above trained models may be concepts that include, for example, models that have been trained as described and further distilled by a general method.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2022/023521 2021-06-11 2022-06-10 訓練装置、推定装置、訓練方法、推定方法及びプログラム Ceased WO2022260178A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2023527953A JP7403032B2 (ja) 2021-06-11 2022-06-10 訓練装置、推定装置、訓練方法、推定方法及びプログラム
US18/533,481 US20240105288A1 (en) 2021-06-11 2023-12-08 Inferring device, training device, method, and non-transitory computer readable medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2021-098292 2021-06-11
JP2021098292 2021-06-11

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/533,481 Continuation US20240105288A1 (en) 2021-06-11 2023-12-08 Inferring device, training device, method, and non-transitory computer readable medium

Publications (1)

Publication Number Publication Date
WO2022260178A1 true WO2022260178A1 (ja) 2022-12-15

Family

ID=84424614

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/023521 Ceased WO2022260178A1 (ja) 2021-06-11 2022-06-10 訓練装置、推定装置、訓練方法、推定方法及びプログラム

Country Status (3)

Country Link
US (1) US20240105288A1 (https=)
JP (1) JP7403032B2 (https=)
WO (1) WO2022260178A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2026074898A1 (ja) * 2024-10-01 2026-04-09 富士通株式会社 情報処理プログラム、情報処理方法、および情報処理装置

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12587274B2 (en) 2023-03-28 2026-03-24 Quantum Generative Materials Llc Satellite optimization management system based on natural language input and artificial intelligence
US12368503B2 (en) 2023-12-27 2025-07-22 Quantum Generative Materials Llc Intent-based satellite transmit management based on preexisting historical location and machine learning
US12603701B2 (en) 2023-12-27 2026-04-14 Quantum Generative Materials Llc Distributed satellite constellation management and control system

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0589074A (ja) * 1991-09-30 1993-04-09 Fujitsu Ltd 二次構造予測装置
WO2021054402A1 (ja) * 2019-09-20 2021-03-25 株式会社 Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ 推定装置、訓練装置、推定方法及び訓練方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2011021279A1 (ja) 2009-08-18 2011-02-24 富士通株式会社 物質の応力を算出する情報処理装置

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0589074A (ja) * 1991-09-30 1993-04-09 Fujitsu Ltd 二次構造予測装置
WO2021054402A1 (ja) * 2019-09-20 2021-03-25 株式会社 Ｐｒｅｆｅｒｒｅｄ Ｎｅｔｗｏｒｋｓ 推定装置、訓練装置、推定方法及び訓練方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2026074898A1 (ja) * 2024-10-01 2026-04-09 富士通株式会社 情報処理プログラム、情報処理方法、および情報処理装置

Also Published As

Publication number Publication date
JP7403032B2 (ja) 2023-12-21
US20240105288A1 (en) 2024-03-28
JPWO2022260178A1 (https=) 2022-12-15

Similar Documents

Publication Publication Date Title
JP7403032B2 (ja) 訓練装置、推定装置、訓練方法、推定方法及びプログラム
CN114580647B (zh) 量子系统的模拟方法、计算设备、装置及存储介质
CN114219076B (zh) 量子神经网络训练方法及装置、电子设备和介质
CN113011593B (zh) 消除量子测量噪声的方法及系统、电子设备和介质
Lehtovaara et al. Solution of time-independent Schrödinger equation by the imaginary time propagation method
US20200286595A1 (en) Simulating electronic structure with quantum annealing devices and artificial neural networks
CN114521263A (zh) 推测装置、训练装置、推测方法以及训练方法
WO2022260179A1 (ja) 訓練装置、訓練方法、プログラム及び推論装置
WO2022260171A1 (ja) 推定装置及びモデル生成方法
CN114707358B (zh) 离子阱量子门保真度优化方法及装置、电子设备和介质
CN115577791B (zh) 基于量子系统的信息处理方法及装置
CN113098802B (zh) 量子噪声信道的逆映射分解方法及装置、电子设备和介质
Yang et al. DMIS: Dynamic mesh-based importance sampling for training physics-informed neural networks
JP2022068327A (ja) ノードグループ化方法、装置及び電子機器
CN114418103B (zh) 基态能量的确定方法、装置、设备及存储介质
CN114897173A (zh) 基于变分量子线路确定PageRank的方法及装置
Ma et al. Bi-orthogonal fPINN: A physics-informed neural network method for solving time-dependent stochastic fractional PDEs
JP2020201566A (ja) 開放量子系のための量子情報処理方法、古典コンピュータ、量子コンピュータ、量子情報処理プログラム、及びデータ構造
JP2022062274A (ja) 関数処理方法、装置及び電子機器
CN113098803A (zh) 量子噪声信道的逆映射分解方法及装置、电子设备和介质
CN114202073B (zh) 脉冲序列生成方法、控制方法、装置、系统及设备
JP2024075646A (ja) 推定装置、訓練装置、推定方法、訓練方法、プログラム及び非一時的コンピュータ可読媒体
Aghaei et al. Pinnies: an efficient physics-informed neural network framework to integral operator problems
JP2024044001A (ja) 量子回路学習システム、量子回路学習方法、量子回路学習プログラム、量子推論システム、量子回路及び量子古典ハイブリッドニューラルネットワーク
WO2022163629A1 (ja) 推定装置、訓練装置、推定方法、生成方法及びプログラム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22820356

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2023527953

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22820356

Country of ref document: EP

Kind code of ref document: A1