ES3014274T3 - Probability distribution learning apparatus and autoencoder learning apparatus - Google Patents
Probability distribution learning apparatus and autoencoder learning apparatus Download PDFInfo
- Publication number
- ES3014274T3 ES3014274T3 ES23156617T ES23156617T ES3014274T3 ES 3014274 T3 ES3014274 T3 ES 3014274T3 ES 23156617 T ES23156617 T ES 23156617T ES 23156617 T ES23156617 T ES 23156617T ES 3014274 T3 ES3014274 T3 ES 3014274T3
- Authority
- ES
- Spain
- Prior art keywords
- probability distribution
- unit
- input data
- normal sound
- parameter
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural 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
- G06N3/04—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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder 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
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- 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
- G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-supervised learning
-
- 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
- G06N3/096—Transfer learning
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- 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
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Signal Processing (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
Se proporciona una técnica de detección de anomalías que ofrece alta precisión y reduce el coste del aprendizaje de modelos normales. El aparato de detección de anomalías incluye una unidad de estimación del grado de anomalía, configurada para estimar el grado de anomalía del equipo objetivo de detección a partir del sonido emitido por dicho equipo (en adelante, «sonido del objetivo de detección») basándose en la asociación entre una primera distribución de probabilidad que indica la distribución del sonido normal emitido por uno o más equipos distintos del equipo objetivo de detección y el sonido normal emitido por dicho equipo (en adelante, «sonido normal para aprendizaje adaptativo»). (Traducción automática con Google Translate, sin valor legal)
Claims (2)
1. Un aparato de aprendizaje de distribución de probabilidad que comprende
una unidad (150) de aprendizaje configurada para desde un sonido normal emitido desde una o más piezas de equipos diferentes del equipo objetivo de detección de anomalías, en lo sucesivo denominado sonido normal aprender, una primera distribución de probabilidad q1(x;0) que indica distribución del sonido normal, comprendiendo la unidad (105) de aprendizaje:
una unidad (110) generadora de datos de entrada configurada para generar datos de entrada x i (i = 1, ..., N) a partir de sonido normal para aprender si (i = 1, ..., N) que es la entrada,
una unidad (120) de estimación de variable latente configurada para estimar una variable latente z0,i (i = 1, ..., N) correspondiente a los datos de entrada x i a partir de los datos de entrada xi generados a partir del sonido normal para el aprendizaje si (i = 1, ..., N) que es de entrada utilizando el parámetro 0 de la primera distribución de probabilidad q i(x;0),
una unidad (130) de cálculo de la función de pérdida configurada para calcular un valor de una función L(0) de pérdida que se utilizará para la optimización del parámetro 0 de la primera distribución de probabilidad qi(x;0) a partir de la variable latente z0,i (i = 1, ..., N),
una unidad (140) de actualización de parámetros configurada para actualizar el parámetro 0 de la primera distribución de probabilidad q1(x;0) con el fin de optimizar el valor de la función de pérdida L(0), y
una unidad (150) de determinación de las condiciones de convergencia configurada para determinar las condiciones de convergencia establecidas de antemano como condiciones de terminación de la actualización de parámetros, producir la salida de la primera distribución de probabilidad q1(x;0) utilizando el parámetro 0 actualizado por la unidad (140) de actualización de parámetros en un caso donde se satisfacen las condiciones de convergencia, y repetir el procesamiento de la unidad (110) de generación de datos de entrada, la unidad (120) de estimación de la variable latente, la unidad (130) de cálculo de la función de pérdida y la unidad (140) de actualización de parámetros en un caso en el que no se satisfacen las condiciones de convergencia, en donde una variable x de la primera distribución de probabilidad q1(x;0) es una variable que indica datos de entrada generados a partir del sonido normal emitido desde la una o más piezas de equipo diferentes del equipo objetivo de detección de anomalías,
en donde la variable x se expresa como x = fK(fK-1(...(f1(z0))...)) utilizando transformación es fi(i = 1, ..., K), en donde K es un número entero de 1 o mayor, y existen transformaciones inversas fi-1 para las transformaciones fi y una variable latente z0,
q0(zü) se establece como una distribución de probabilidad de la variable latente z0,
una densidad de probabilidad q1(x;0) de probabilidad de los datos x de entrada se calcula utilizando la densidad q0(z0) de probabilidad de la variable latente z0 = f1-1(f2-1(...(fK-1(x))...)) correspondiente a los datos x de entrada al menos una transformación inversas de las transformaciones fi(i = 1, ..., K) es una normalización adaptativa por lotes.
2. El aparato de aprendizaje de distribución de probabilidad según la reivindicación 1,
en donde, al menos, una transformación inversa de las transformaciones f i(i = 1, ..., K) es una transformación lineal, y
una matriz correspondiente a la transformación lineal se expresa como un producto de una matriz triangular inferior y una matriz triangular superior o como un producto de una matriz triangular inferior, una matriz diagonal y una matriz triangular superior.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2018151412 | 2018-08-10 | ||
| JP2018209416 | 2018-11-07 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| ES3014274T3 true ES3014274T3 (en) | 2025-04-21 |
Family
ID=69415502
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| ES19848621T Active ES2979165T3 (es) | 2018-08-10 | 2019-07-04 | Aparato de detección de anomalías y programa |
| ES23156617T Active ES3014274T3 (en) | 2018-08-10 | 2019-07-04 | Probability distribution learning apparatus and autoencoder learning apparatus |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| ES19848621T Active ES2979165T3 (es) | 2018-08-10 | 2019-07-04 | Aparato de detección de anomalías y programa |
Country Status (6)
| Country | Link |
|---|---|
| US (1) | US12190904B2 (es) |
| EP (3) | EP4216216B1 (es) |
| JP (2) | JP7140194B2 (es) |
| CN (2) | CN118348951A (es) |
| ES (2) | ES2979165T3 (es) |
| WO (1) | WO2020031570A1 (es) |
Families Citing this family (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11928208B2 (en) * | 2018-10-02 | 2024-03-12 | Nippon Telegraph And Telephone Corporation | Calculation device, calculation method, and calculation program |
| US20200285997A1 (en) * | 2019-03-04 | 2020-09-10 | Iocurrents, Inc. | Near real-time detection and classification of machine anomalies using machine learning and artificial intelligence |
| KR20200108523A (ko) * | 2019-03-05 | 2020-09-21 | 주식회사 엘렉시 | 이상 패턴 감지 시스템 및 방법 |
| DE112020006948B4 (de) * | 2020-05-28 | 2024-06-20 | Mitsubishi Electric Corporation | Überwachungsvorrichtung eines anlagenzustands und verfahren zur überwachung eines anlagenzustands |
| WO2021241576A1 (ja) * | 2020-05-29 | 2021-12-02 | 株式会社ダイセル | 異常変調原因特定装置、異常変調原因特定方法及び異常変調原因特定プログラム |
| JP7604486B2 (ja) * | 2020-05-29 | 2024-12-23 | 株式会社ダイセル | 異常変調原因特定装置、異常変調原因特定方法及び異常変調原因特定プログラム |
| JP7399797B2 (ja) * | 2020-06-15 | 2023-12-18 | 株式会社日立製作所 | 異常度算出システムおよび方法 |
| DE102020208642A1 (de) * | 2020-07-09 | 2022-01-13 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren und Vorrichtung zur Anomaliedetektion in technischen Systemen |
| JP7521968B2 (ja) * | 2020-08-19 | 2024-07-24 | 日鉄テックスエンジ株式会社 | 設備監視支援装置、方法及びプログラム |
| US20230366729A1 (en) * | 2020-09-24 | 2023-11-16 | Si Synergy Technology Co., Ltd. | Trained autoencoder, trained autoencoder generation method, non-stationary vibration detection method, non-stationary vibration detection device, and computer program |
| EP3975063A1 (en) * | 2020-09-25 | 2022-03-30 | Robert Bosch GmbH | Device for and computer implemented method of machine learning |
| CN112767331B (zh) * | 2021-01-08 | 2022-10-04 | 北京航空航天大学 | 基于零样本学习的图像异常检测方法 |
| US11443758B2 (en) * | 2021-02-09 | 2022-09-13 | International Business Machines Corporation | Anomalous sound detection with timbre separation |
| JP7517482B2 (ja) * | 2021-02-09 | 2024-07-17 | 日本電信電話株式会社 | 学習装置、異常検知装置、学習方法、異常検知方法、及びプログラム |
| JP7548843B2 (ja) * | 2021-02-22 | 2024-09-10 | 株式会社日立製作所 | 異常度算出システムおよび方法 |
| US20220284283A1 (en) * | 2021-03-08 | 2022-09-08 | Nvidia Corporation | Neural network training technique |
| KR20220127606A (ko) * | 2021-03-11 | 2022-09-20 | 에스케이플래닛 주식회사 | 무압축 합성곱 신경망 기반 소리 이상 탐지 장치 및 방법 |
| JP7614025B2 (ja) * | 2021-06-14 | 2025-01-15 | 株式会社日立製作所 | 異常検知システム |
| CN113762333B (zh) * | 2021-07-20 | 2023-02-28 | 广东省科学院智能制造研究所 | 一种基于双流联合密度估计的无监督异常检测方法和系统 |
| JP7103539B1 (ja) | 2022-01-17 | 2022-07-20 | 富士電機株式会社 | 運転支援装置、運転支援方法及びプログラム |
| US12259968B2 (en) * | 2022-02-11 | 2025-03-25 | Microsoft Technology Licensing, Llc | Detecting anomalous post-authentication behavior for a workload identity |
| CN116778002A (zh) * | 2022-03-10 | 2023-09-19 | 华为技术有限公司 | 编解码方法、装置、设备、存储介质及计算机程序产品 |
| CN114783417B (zh) * | 2022-04-29 | 2023-03-24 | 北京远鉴信息技术有限公司 | 一种语音检测方法、装置、电子设备及存储介质 |
| JP2024036930A (ja) * | 2022-09-06 | 2024-03-18 | 富士通株式会社 | 機械学習プログラム、機械学習方法および情報処理装置 |
| JP7510979B2 (ja) * | 2022-09-22 | 2024-07-04 | 株式会社日立製作所 | 異常音のデータを生成する装置及び方法 |
| KR102687021B1 (ko) * | 2023-07-13 | 2024-07-22 | 주식회사 마키나락스 | 장비의 이상 원인을 예측하고, 예측 결과를 플랫폼을 통해 제공하기 위한 방법 |
| CN117095216B (zh) * | 2023-08-23 | 2024-06-04 | 湖北省地质调查院 | 基于对抗生成网络的模型训练方法、系统、设备及介质 |
| WO2025052675A1 (ja) * | 2023-09-08 | 2025-03-13 | 日本電信電話株式会社 | 学習装置、異常検知装置、学習方法、異常検知方法、及びプログラム |
| CN119903419B (zh) * | 2024-12-30 | 2026-03-17 | 西北工业大学 | 一种基于自编码器的航空发动机装配质量异常检测和特征推断的方法 |
| JP7833092B1 (ja) * | 2025-11-05 | 2026-03-18 | 株式会社インターネットイニシアティブ | 異常管理装置、および異常管理方法 |
| JP7804825B1 (ja) * | 2025-11-12 | 2026-01-22 | 株式会社インターネットイニシアティブ | 異常管理装置、および異常管理方法 |
Family Cites Families (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3012449B2 (ja) | 1994-01-31 | 2000-02-21 | バブコック日立株式会社 | 音響信号の識別方法および装置 |
| EP0666542A3 (en) * | 1994-02-04 | 1996-05-15 | Fuji Facom Corp | Multimedia system for monitoring and controlling processes. |
| US6139505A (en) * | 1998-10-14 | 2000-10-31 | Murphy; Raymond L. H. | Method and apparatus for displaying lung sounds and performing diagnosis based on lung sound analysis |
| JP4303135B2 (ja) | 2004-01-09 | 2009-07-29 | 独立行政法人科学技術振興機構 | 歪みあり符号方法及び装置、歪みあり符号化プログラム及び記録媒体 |
| JP4100414B2 (ja) * | 2005-04-25 | 2008-06-11 | 松下電工株式会社 | 設備監視方法および設備監視装置 |
| JP4200332B2 (ja) * | 2006-08-29 | 2008-12-24 | パナソニック電工株式会社 | 異常監視装置、異常監視方法 |
| JP5767825B2 (ja) * | 2011-02-28 | 2015-08-19 | 綜合警備保障株式会社 | 音処理装置および音処理方法 |
| JP6236282B2 (ja) * | 2013-10-21 | 2017-11-22 | 株式会社日立ハイテクノロジーズ | 異常検出装置、異常検出方法、及びコンピュータ読み取り可能な記憶媒体 |
| JP2015161745A (ja) * | 2014-02-26 | 2015-09-07 | 株式会社リコー | パターン認識システムおよびプログラム |
| JP2016007800A (ja) * | 2014-06-25 | 2016-01-18 | 株式会社リコー | 異常検知システム、電子機器、異常検知方法およびプログラム |
| US9576583B1 (en) * | 2014-12-01 | 2017-02-21 | Cedar Audio Ltd | Restoring audio signals with mask and latent variables |
| US10068445B2 (en) * | 2015-06-24 | 2018-09-04 | Google Llc | Systems and methods of home-specific sound event detection |
| CN105244038A (zh) * | 2015-09-30 | 2016-01-13 | 金陵科技学院 | 一种基于hmm的选矿设备故障异常音频分析与识别方法 |
| JP6377592B2 (ja) * | 2015-11-09 | 2018-08-22 | 日本電信電話株式会社 | 異常音検出装置、異常音検出学習装置、これらの方法及びプログラム |
| EP3385889A4 (en) * | 2015-12-01 | 2019-07-10 | Preferred Networks, Inc. | ANOMALIC DETECTION SYSTEM, ANOMALY DETECTION METHOD, ANOMALIC DETECTION PROGRAM, AND METHOD OF GENERATING A LEARNED MODEL |
| JP6709277B2 (ja) | 2016-04-01 | 2020-06-10 | 日本電信電話株式会社 | 異常音検出装置、異常音検出学習装置、異常音サンプリング装置、これらの方法及びプログラム |
| US10248533B1 (en) * | 2016-07-11 | 2019-04-02 | State Farm Mutual Automobile Insurance Company | Detection of anomalous computer behavior |
| US20190377325A1 (en) * | 2017-01-23 | 2019-12-12 | Nrg Systems, Inc. | System and methods of novelty detection using non-parametric machine learning |
| CN110352349B (zh) * | 2017-02-15 | 2023-01-31 | 日本电信电话株式会社 | 异常音检测装置、异常度计算装置、异常音生成装置、异常信号检测装置、及其方法、记录介质 |
| CN106941005A (zh) * | 2017-02-24 | 2017-07-11 | 华南理工大学 | 一种基于语音声学特征的声带异常检测方法 |
| JP2018156151A (ja) * | 2017-03-15 | 2018-10-04 | ファナック株式会社 | 異常検知装置及び機械学習装置 |
| JP6947219B2 (ja) * | 2017-09-06 | 2021-10-13 | 日本電信電話株式会社 | 異常音検知装置、異常モデル学習装置、異常検知装置、異常音検知方法、異常音生成装置、異常データ生成装置、異常音生成方法、およびプログラム |
| EP3477553B1 (en) * | 2017-10-27 | 2023-08-30 | Robert Bosch GmbH | Method for detecting an anomalous image among a first dataset of images using an adversarial autoencoder |
| JPWO2019087987A1 (ja) * | 2017-11-02 | 2020-11-12 | 日本電信電話株式会社 | 異常検知装置、異常検知方法、及びプログラム |
| US11157782B2 (en) * | 2017-11-16 | 2021-10-26 | International Business Machines Corporation | Anomaly detection in multidimensional time series data |
| US10776239B2 (en) * | 2017-11-30 | 2020-09-15 | International Business Machines Corporation | Tape library integrated failure indication based on cognitive sound and vibration analysis |
| WO2019118644A1 (en) * | 2017-12-14 | 2019-06-20 | D-Wave Systems Inc. | Systems and methods for collaborative filtering with variational autoencoders |
| CN111742462B (zh) * | 2018-02-28 | 2024-11-19 | 罗伯特·博世有限公司 | 用于基于音频和振动的功率分配装备状况监测的系统和方法 |
| JP6930503B2 (ja) * | 2018-07-20 | 2021-09-01 | 日本電信電話株式会社 | 異常検知装置、異常検知方法、およびプログラム |
| US11475910B2 (en) * | 2020-02-11 | 2022-10-18 | Purdue Research Foundation | System and methods for machine anomaly detection based on sound spectrogram images and neural networks |
-
2019
- 2019-07-04 EP EP23156617.5A patent/EP4216216B1/en active Active
- 2019-07-04 CN CN202410356501.7A patent/CN118348951A/zh active Pending
- 2019-07-04 US US17/266,240 patent/US12190904B2/en active Active
- 2019-07-04 ES ES19848621T patent/ES2979165T3/es active Active
- 2019-07-04 EP EP19848621.9A patent/EP3836142B1/en active Active
- 2019-07-04 CN CN201980052478.XA patent/CN112567460B/zh active Active
- 2019-07-04 JP JP2020536385A patent/JP7140194B2/ja active Active
- 2019-07-04 WO PCT/JP2019/026556 patent/WO2020031570A1/ja not_active Ceased
- 2019-07-04 ES ES23156617T patent/ES3014274T3/es active Active
- 2019-07-04 EP EP23156610.0A patent/EP4216215A1/en not_active Withdrawn
-
2022
- 2022-04-06 JP JP2022063343A patent/JP7322997B2/ja active Active
Also Published As
| Publication number | Publication date |
|---|---|
| JP7322997B2 (ja) | 2023-08-08 |
| CN112567460B (zh) | 2024-11-15 |
| EP3836142A1 (en) | 2021-06-16 |
| EP3836142B1 (en) | 2024-04-03 |
| EP3836142A4 (en) | 2022-08-17 |
| EP4216215A1 (en) | 2023-07-26 |
| JP2022082713A (ja) | 2022-06-02 |
| CN118348951A (zh) | 2024-07-16 |
| JP7140194B2 (ja) | 2022-09-21 |
| EP4216216B1 (en) | 2025-02-19 |
| EP4216216A1 (en) | 2023-07-26 |
| CN112567460A (zh) | 2021-03-26 |
| WO2020031570A1 (ja) | 2020-02-13 |
| ES2979165T3 (es) | 2024-09-24 |
| JPWO2020031570A1 (ja) | 2021-08-26 |
| US12190904B2 (en) | 2025-01-07 |
| US20210327456A1 (en) | 2021-10-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| ES3014274T3 (en) | Probability distribution learning apparatus and autoencoder learning apparatus | |
| CN111401138B (zh) | 生成对抗神经网络训练过程的对抗优化方法 | |
| SG10201805974UA (en) | Neural network system and operating method of neural network system | |
| GB2578711A (en) | Text data representation learning using random document embedding | |
| US10635078B2 (en) | Simulation system, simulation method, and simulation program | |
| Zhang et al. | A new extension of newton algorithm for nonlinear system modelling using RBF neural networks | |
| GB2583623A (en) | Fusing sparse kernels to approximate a full kernel of a convolutional neural network | |
| Qiu et al. | An ellipsoidal Newton’s iteration method of nonlinear structural systems with uncertain-but-bounded parameters | |
| Zhang et al. | A dual interpolation boundary face method for three-dimensional potential problems | |
| KR20250018557A (ko) | 전력 증폭기 모델의 획득 방법, 장치 및 전력 증폭기 모델 | |
| GB2602238A (en) | Language statement processing in computing system | |
| Manghi et al. | Generalized additive partial linear models for analyzing correlated data | |
| Shihab et al. | New operational matrices of shifted fourth chebyshev wavelets | |
| Wang | Uncertainty index based consistency measurement and priority generation with interval probabilities in the analytic hierarchy process | |
| JPWO2022130498A5 (es) | ||
| Malarvezhi et al. | Particle filter with novel resampling algorithm: A diversity enhanced particle filter | |
| Bai et al. | Observation Error Handling Methods for Data Assimilation Coupled with Fuzzy Control Algorithms. | |
| Lazov et al. | A general methodology for population analysis | |
| JP7341868B2 (ja) | 情報処理装置、情報処理方法およびプログラム | |
| Vodolazskii et al. | Minimax problems of discrete optimization invariant under majority operators | |
| Zhong et al. | An information geometry algorithm for distribution control | |
| Meng et al. | The ordered weighted geometric averaging algorithm to multiple attribute decision making within triangular fuzzy numbers based on the mean area measurement method1 | |
| Antonova et al. | Recognition of nonlinear functions for estimating region of efficiency in LP τ-search with averaging | |
| Pelling et al. | Adaptive reduced order modelling of acoustic LTI systems with input–output dead time | |
| Dyusembaev et al. | On exact solutions of recognition problems based on the neural-network approach. |