[go: up one dir, main page]

MX2018013242A - Metodo, aparato y programa de computadora para generar sistemas de aprendizaje automatizados, robustos y sistemas de aprendizaje automatizados formados de prueba. - Google Patents

Metodo, aparato y programa de computadora para generar sistemas de aprendizaje automatizados, robustos y sistemas de aprendizaje automatizados formados de prueba.

Info

Publication number
MX2018013242A
MX2018013242A MX2018013242A MX2018013242A MX2018013242A MX 2018013242 A MX2018013242 A MX 2018013242A MX 2018013242 A MX2018013242 A MX 2018013242A MX 2018013242 A MX2018013242 A MX 2018013242A MX 2018013242 A MX2018013242 A MX 2018013242A
Authority
MX
Mexico
Prior art keywords
learning systems
automated
neural network
computer program
robust
Prior art date
Application number
MX2018013242A
Other languages
English (en)
Inventor
Wong Eric
Schmidt Frank
Hendrik Metzen Jan
Zico Kolter Jeremy
Original Assignee
Bosch Gmbh Robert
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 Bosch Gmbh Robert filed Critical Bosch Gmbh Robert
Publication of MX2018013242A publication Critical patent/MX2018013242A/es

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
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
    • G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
    • 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
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine 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
    • G06N3/04—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
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • 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
    • G06N3/047—Probabilistic or stochastic 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
    • G06N3/048—Activation functions
    • 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
    • G06N3/0499—Feedforward 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
    • G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
    • 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
    • G06N3/09—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
    • G06N3/094—Adversarial 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Automation & Control Theory (AREA)
  • Probability & Statistics with Applications (AREA)
  • Image Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Feedback Control In General (AREA)

Abstract

La presente invención pertenece a un método para entrenar la red neural 100, un método para probar la red neuronal 100 así como un método para detectar ejemplos adversos, los cuales pueden engañar a la red neural 100, una clasificación superpuesta es propagada hacia atrás a través de la segunda red neural 500, Maryland el valor de salida de la segunda red neural 500 es utilizado para determinar si la entrada de la red neuronal 100 es un ejemplo adverso; los métodos establecidos de la presente invención se basan en esta utilización de la segunda red neural 500; la presente invención además pertenece a un programa de computadora y un aparato los cuales están configurados para llevar a cabo dichos métodos.
MX2018013242A 2018-05-30 2018-10-29 Metodo, aparato y programa de computadora para generar sistemas de aprendizaje automatizados, robustos y sistemas de aprendizaje automatizados formados de prueba. MX2018013242A (es)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201862677896P 2018-05-30 2018-05-30
US201862736858P 2018-09-26 2018-09-26

Publications (1)

Publication Number Publication Date
MX2018013242A true MX2018013242A (es) 2019-12-02

Family

ID=66589347

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2018013242A MX2018013242A (es) 2018-05-30 2018-10-29 Metodo, aparato y programa de computadora para generar sistemas de aprendizaje automatizados, robustos y sistemas de aprendizaje automatizados formados de prueba.

Country Status (9)

Country Link
US (2) US11676025B2 (es)
EP (1) EP3576021B1 (es)
KR (1) KR102790856B1 (es)
CN (1) CN110554602B (es)
AU (1) AU2018256516A1 (es)
BR (1) BR102019001258A2 (es)
CA (1) CA3022728A1 (es)
DE (1) DE102018218586A1 (es)
MX (1) MX2018013242A (es)

Families Citing this family (48)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11547052B1 (en) * 2018-10-10 2023-01-10 Hydro-Gear Limited Partnership Audible operator feedback for riding lawn mower applications
US11200438B2 (en) 2018-12-07 2021-12-14 Dus Operating Inc. Sequential training method for heterogeneous convolutional neural network
US11200318B2 (en) * 2018-12-28 2021-12-14 Mcafee, Llc Methods and apparatus to detect adversarial malware
EP3906508B1 (en) * 2018-12-31 2024-03-13 Intel Corporation Securing systems employing artificial intelligence
JP7073286B2 (ja) * 2019-01-10 2022-05-23 株式会社日立製作所 データ生成装置、予測器学習装置、データ生成方法、及び学習方法
US11625487B2 (en) * 2019-01-24 2023-04-11 International Business Machines Corporation Framework for certifying a lower bound on a robustness level of convolutional neural networks
US11068069B2 (en) * 2019-02-04 2021-07-20 Dus Operating Inc. Vehicle control with facial and gesture recognition using a convolutional neural network
US12456030B2 (en) * 2019-11-14 2025-10-28 Qualcomm Incorporated Phase selective convolution with dynamic weight selection
CN111027628B (zh) * 2019-12-12 2022-03-11 支付宝(杭州)信息技术有限公司 一种模型确定方法和系统
EP3859598B1 (en) * 2020-02-03 2025-07-16 Robert Bosch GmbH Training method for a generator neural network imposing data equivariances
US10846407B1 (en) 2020-02-11 2020-11-24 Calypso Ai Corp Machine learning model robustness characterization
US11568021B2 (en) 2020-02-21 2023-01-31 Alibaba Group Holding Limited Vector-vector multiplication techniques for processing systems
CN111368886B (zh) * 2020-02-25 2023-03-21 华南理工大学 一种基于样本筛选的无标注车辆图片分类方法
DE102020202870A1 (de) * 2020-03-06 2021-09-09 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren zur Validierung und Auswahl auf maschinellem Lernen basierender Modelle zur Zustandsüberwachung einer Maschine
CN111401292B (zh) * 2020-03-25 2023-05-26 成都东方天呈智能科技有限公司 一种融合红外图像训练的人脸识别网络构建方法
CN111461307B (zh) * 2020-04-02 2022-04-29 武汉大学 一种基于生成对抗网络的通用扰动生成方法
EP3896613B1 (en) * 2020-04-14 2024-06-05 Robert Bosch GmbH Device and method for training a classifier and assessing the robustness of a classifier
US20210334646A1 (en) * 2020-04-28 2021-10-28 International Business Machines Corporation Robustness-aware quantization for neural networks against weight perturbations
DE102020114339A1 (de) * 2020-05-28 2021-12-02 Ebm-Papst Mulfingen Gmbh & Co. Kg Verfahren zum Betreiben eines Ventilatorsystems und Ventilatorsystem mit einem rückwärtsgekrümmten Radialventilator
US12020166B2 (en) * 2020-05-29 2024-06-25 Robert Bosch Gmbh Meta-learned, evolution strategy black box optimization classifiers
DE102020207004A1 (de) * 2020-06-04 2021-12-09 Robert Bosch Gesellschaft mit beschränkter Haftung Regularisiertes Training neuronaler Netzwerke
CN111709878B (zh) 2020-06-17 2023-06-23 北京百度网讯科技有限公司 人脸超分辨率实现方法、装置、电子设备及存储介质
DE102020208737A1 (de) 2020-07-13 2022-01-13 Volkswagen Aktiengesellschaft Verfahren und Vorrichtung zum Bewerten und Zertifizieren einer Robustheit eines KI-basierten Informationsverarbeitungssystems
US12340574B2 (en) * 2020-07-28 2025-06-24 Mitsubishi Electric Corporation Learning utilization system, utilizing device, learning device, non-transitory computer-readable medium, and learning utilization method
CN116210007A (zh) * 2020-09-02 2023-06-02 大众汽车股份公司 在交通工具运行期间控制驾驶员辅助系统的方法
KR102598909B1 (ko) * 2020-09-03 2023-11-06 부산대학교 산학협력단 적대적 사례에 강인한 심층 신경망 모델을 위한 입력 장치 및 방법
US12210966B2 (en) * 2020-09-28 2025-01-28 Robert Bosch Gmbh Method and system for probably robust classification with detection of adversarial examples
DE102020212147A1 (de) * 2020-09-28 2022-03-31 Robert Bosch Gesellschaft mit beschränkter Haftung Datenbasierte Fortschreibung des Trainings von Klassifikatornetzwerken
US11687619B2 (en) * 2020-10-02 2023-06-27 Robert Bosch Gmbh Method and system for an adversarial training using meta-learned initialization
DE102020213058A1 (de) 2020-10-15 2022-04-21 Volkswagen Aktiengesellschaft Verfahren und Vorrichtung zum teilautomatisierten oder vollautomatisierten Steuern eines Fahrzeugs
DE102020213057A1 (de) 2020-10-15 2022-04-21 Volkswagen Aktiengesellschaft Verfahren und Vorrichtung zum Überprüfen eines beim teilautomatisierten oder vollautomatisierten Steuern eines Fahrzeugs verwendeten KI-basierten Informationsverarbeitungssystems
WO2022079901A1 (ja) * 2020-10-16 2022-04-21 日本電気株式会社 情報処理装置、情報処理方法および記録媒体
US12282839B2 (en) * 2020-11-25 2025-04-22 The Boeing Company Constraint based inference and machine learning system
JP7561013B2 (ja) 2020-11-27 2024-10-03 ロベルト・ボッシュ・ゲゼルシャフト・ミト・ベシュレンクテル・ハフツング データ処理装置、ニューラルネットワークの深層学習の方法及びプログラム
US11907334B2 (en) * 2020-12-08 2024-02-20 International Business Machines Corporation Neural network negative rule extraction
CN116635867A (zh) * 2020-12-21 2023-08-22 罗伯特·博世有限公司 训练分类器或回归器以对时间序列进行鲁棒的分类和回归的方法和设备
US12488279B2 (en) 2020-12-28 2025-12-02 International Business Machines Corporation Domain-specific constraints for predictive modeling
US12307333B2 (en) * 2020-12-28 2025-05-20 International Business Machines Corporation Loss augmentation for predictive modeling
US12165057B2 (en) 2020-12-28 2024-12-10 International Business Machines Corporation Split-net configuration for predictive modeling
KR102875463B1 (ko) * 2021-04-21 2025-10-24 한국전자통신연구원 뉴럴 네트워크 학습 장치 및 방법
EP4083859A1 (en) * 2021-04-30 2022-11-02 Robert Bosch GmbH Improved training of classifiers and/or regressors on uncertain training data
EP4156025A1 (en) * 2021-09-23 2023-03-29 Robert Bosch GmbH Device and method for generating training data for a machine learning system
CN114200841B (zh) * 2021-12-13 2023-05-23 电子科技大学 一种基于模糊反步的网联汽车系统安全控制方法
CN115114395B (zh) * 2022-04-15 2024-03-19 腾讯科技（深圳）有限公司 内容检索及模型训练方法、装置、电子设备和存储介质
CN114756214B (zh) * 2022-06-15 2022-08-12 中国海洋大学 基于OpenCV和插件的图像处理方法、装置
KR20250074917A (ko) * 2023-11-21 2025-05-28 이화여자대학교 산학협력단 적대적 공격에 강건한 이상 탐지 방법
EP4582884A1 (de) * 2024-01-03 2025-07-09 Siemens Aktiengesellschaft Verfahren zum erzeugen einer betriebssteuerung für eine maschine mittels einer elektronischen recheneinrichtung, computerprogrammprodukt, computerlesbares speichermedium sowie elektronische recheneinrichtung
CN119312845B (zh) * 2024-09-24 2025-09-09 电子科技大学 一种多功能雷达干扰决策网络编码方法

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4884216A (en) * 1987-11-09 1989-11-28 Michael Kuperstein Neural network system for adaptive sensory-motor coordination of multijoint robots for single postures
US8688616B2 (en) * 2010-06-14 2014-04-01 Blue Prism Technologies Pte. Ltd. High-dimensional data analysis
US8712940B2 (en) * 2011-05-31 2014-04-29 International Business Machines Corporation Structural plasticity in spiking neural networks with symmetric dual of an electronic neuron
CN104392143B (zh) * 2014-12-09 2017-05-17 北京四方继保自动化股份有限公司 一种自适应量子神经网络汽轮机故障趋势预测方法
CN105512725B (zh) * 2015-12-14 2018-08-28 杭州朗和科技有限公司 一种神经网络的训练方法和设备
US11144889B2 (en) * 2016-04-06 2021-10-12 American International Group, Inc. Automatic assessment of damage and repair costs in vehicles
US10282656B2 (en) 2017-01-11 2019-05-07 Thomas Danaher Harvey Method and device for detecting unauthorized tranfer between persons
US10810481B2 (en) * 2017-01-11 2020-10-20 Thomas Danaher Harvey Method and system to count movements of persons from vibrations in a floor
DE102018200724A1 (de) 2017-04-19 2018-10-25 Robert Bosch Gmbh Verfahren und Vorrichtung zum Verbessern der Robustheit gegen "Adversarial Examples"
WO2019227294A1 (zh) * 2018-05-28 2019-12-05 华为技术有限公司 图像处理方法、相关设备及计算机存储介质
DE102018208763A1 (de) 2018-06-04 2019-12-05 Robert Bosch Gmbh Verfahren, Vorrichtung und Computerprogramm zum Betreiben eines maschinellen Lernsystems

Also Published As

Publication number Publication date
DE102018218586A1 (de) 2020-01-09
US20200026996A1 (en) 2020-01-23
AU2018256516A1 (en) 2019-12-19
CA3022728A1 (en) 2019-11-30
CN110554602B (zh) 2024-10-01
KR20190136893A (ko) 2019-12-10
US20190370660A1 (en) 2019-12-05
KR102790856B1 (ko) 2025-04-07
EP3576021A1 (en) 2019-12-04
BR102019001258A2 (pt) 2019-12-03
US11676025B2 (en) 2023-06-13
EP3576021B1 (en) 2024-10-30
CN110554602A (zh) 2019-12-10
US11386328B2 (en) 2022-07-12

Similar Documents

Publication Publication Date Title
MX2018013242A (es) Metodo, aparato y programa de computadora para generar sistemas de aprendizaje automatizados, robustos y sistemas de aprendizaje automatizados formados de prueba.
Hussain et al. Interpretive structural modeling-analytic network process integrated framework for evaluating sustainable supply chain management alternatives
EP3686782C0 (en) LEARNING METHOD AND LEARNING DEVICE FOR OBJECT DETECTOR USING TARGET OBJECT ESTIMATION NETWORK AND TARGET OBJECT FUSION NETWORK, TESTING METHOD AND TESTING DEVICE USING THEM
Qian et al. The Gaussian CLs method for searches of new physics
MX2024015892A (es) Sistemas y metodos para determinar defectos en objetos fisicos
Cribbs et al. Mathematics identity and student persistence in engineering
MX2022005752A (es) Sistema de análisis de imágenes para pruebas en la fabricación.
GB2563523A (en) Electromagnetic (EM) defect detection methods and systems employing deconvolved raw measurements
PH12016000112B1 (en) Protocol evaluator
PH12020550509A1 (en) System for identifying pests and monitoring information through image analysis, and monitoring method using same
MX2020004068A (es) Sistemas y métodos para el seguimiento de portadores de bienes.
SG10201802739PA (en) Neural network systems
WO2019079621A8 (en) Method and system for penetration testing classification based on captured log data
IN2015CH04673A (es)
GB2571645A (en) Automatic classification of drilling reports with deep natural language processing
KR20180084576A (ko) 행동-인식 연결 학습 기반 의도 이해 장치, 방법 및 그 방법을 수행하기 위한 기록 매체
MX2019003101A (es) Estimación de vida útil remanente (rul) basada en casos fallidos y censurados de entidades.
EP3671244A4 (en) SOH ANALYSIS DEVICE AND METHOD
MX2020013214A (es) Actualizacion de graficos ejecutables.
GB2546666A (en) Optical computing device diagnostics and treatment
WO2016050412A3 (en) Monitoring means and monitoring method for monitoring at least one step of a process run on an industrial site
GB2566651A (en) Systems and methods of providing decision support to first responders
EP3686785C0 (en) LEARNING METHOD AND DEVICE FOR CNN-BASED FLUCTUATION-RESISTANT OBJECT DETECTOR USING TARGET OBJECT ESTIMATION NETWORK AND TESTING METHOD AND DEVICE USING THE SAME
MX2016003852A (es) Plataforma para generar trayectorias laborales personalizadas.
EP3745137A4 (en) SAMPLE MEASURING DEVICE, REAGENT CONTAINER AND SAMPLE MEASUREMENT METHOD