JP7493380B2 - 機械学習システム、並びに、機械学習システムを構成する方法、コンピュータプログラム及び装置 - Google Patents

機械学習システム、並びに、機械学習システムを構成する方法、コンピュータプログラム及び装置 Download PDF

Info

Publication number
JP7493380B2
JP7493380B2 JP2020081985A JP2020081985A JP7493380B2 JP 7493380 B2 JP7493380 B2 JP 7493380B2 JP 2020081985 A JP2020081985 A JP 2020081985A JP 2020081985 A JP2020081985 A JP 2020081985A JP 7493380 B2 JP7493380 B2 JP 7493380B2
Authority
JP
Japan
Prior art keywords
machine learning
learning system
filter
images
variables
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
Application number
JP2020081985A
Other languages
English (en)
Japanese (ja)
Other versions
JP2020184341A5 (cg-RX-API-DMAC7.html
JP2020184341A (ja
Inventor
プファイル トーマス
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.)
Robert Bosch GmbH
Original Assignee
Robert Bosch GmbH
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 Robert Bosch GmbH filed Critical Robert Bosch GmbH
Publication of JP2020184341A publication Critical patent/JP2020184341A/ja
Publication of JP2020184341A5 publication Critical patent/JP2020184341A5/ja
Application granted granted Critical
Publication of JP7493380B2 publication Critical patent/JP7493380B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • 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
    • G06N3/0495—Quantised networks; Sparse networks; Compressed networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
    • 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
    • G06N3/08—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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Neurology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)
  • Business, Economics & Management (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
JP2020081985A 2019-05-08 2020-05-07 機械学習システム、並びに、機械学習システムを構成する方法、コンピュータプログラム及び装置 Active JP7493380B2 (ja)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102019206621.6 2019-05-08
DE102019206621.6A DE102019206621A1 (de) 2019-05-08 2019-05-08 Maschinelles Lernsystem, sowie ein Verfahren, ein Computerprogramm und eine Vorrichtung zum Erstellen des maschinellen Lernsystems

Publications (3)

Publication Number Publication Date
JP2020184341A JP2020184341A (ja) 2020-11-12
JP2020184341A5 JP2020184341A5 (cg-RX-API-DMAC7.html) 2023-08-29
JP7493380B2 true JP7493380B2 (ja) 2024-05-31

Family

ID=70277229

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2020081985A Active JP7493380B2 (ja) 2019-05-08 2020-05-07 機械学習システム、並びに、機械学習システムを構成する方法、コンピュータプログラム及び装置

Country Status (6)

Country Link
US (1) US11790218B2 (cg-RX-API-DMAC7.html)
EP (1) EP3736742B1 (cg-RX-API-DMAC7.html)
JP (1) JP7493380B2 (cg-RX-API-DMAC7.html)
KR (1) KR20200130153A (cg-RX-API-DMAC7.html)
CN (1) CN111914990B (cg-RX-API-DMAC7.html)
DE (1) DE102019206621A1 (cg-RX-API-DMAC7.html)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11755469B2 (en) * 2020-09-24 2023-09-12 Argo AI, LLC System for executing structured tests across a fleet of autonomous vehicles
US12356219B2 (en) * 2020-10-15 2025-07-08 Qualcomm Incorporated Update resolution signaling in federated learning
US12517983B2 (en) * 2022-08-22 2026-01-06 Nec Corporation SNR detection with few-shot trained models

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3827037B2 (ja) * 1997-05-23 2006-09-27 ソニー株式会社 学習方法および装置、ロボット、並びに記録媒体
US20180336469A1 (en) * 2017-05-18 2018-11-22 Qualcomm Incorporated Sigma-delta position derivative networks
CN107633223A (zh) * 2017-09-15 2018-01-26 深圳市唯特视科技有限公司 一种基于深层对抗网络的视频人体属性识别方法
DE102017218889A1 (de) * 2017-10-23 2019-04-25 Robert Bosch Gmbh Unscharf parametriertes KI-Modul sowie Verfahren zum Betreiben
DE102018220608A1 (de) 2018-09-26 2020-03-26 Robert Bosch Gmbh Maschinelles Lernsystem, sowie ein Verfahren, ein Computerprogramm und eine Vorrichtung zum Erstellen des maschinellen Lernsystems
US10999606B2 (en) * 2019-01-08 2021-05-04 Intel Corporation Method and system of neural network loop filtering for video coding
US11481991B2 (en) * 2020-07-15 2022-10-25 Visual Defence Inc. System and method for detecting and transmitting incidents of interest of a roadway to a remote server
US12694262B2 (en) * 2021-03-25 2026-07-28 Smart Engines Service, LLC Almost-indirect convolution in quantized neural networks

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
Hyunhoon LEE et al.,"Fixed-Point Quantization of 3D Convolutional Neural Networks for Energy-Efficient Action Recognition",2018 International SoC Design Conference (ISOCC),2018年11月,DOI: 10.1109/ISOCC.2018.8649987
Md Zahangir Alom et al.,"Effective Quantization Approaches for Recurrent Neural Networks",arXiv,2018年02月07日,DOI: 10.48550/arXiv.1802.02615
Okan Kopuklu et al.,"Resource Efficient 3D Convolutional Neural Networks",arXiv,2021年10月18日,DOI: 10.48550/arXiv.1904.02422
Shuiwang JI et al.,"3D Convolutional Neural Networks for Human Action Recognition",IEEE Transactions on Pattern Analysis and Machine Intelligence,2013年01月,Vol. 35, No. 1,pp.221-231,DOI: 10.1109/TPAMI.2012.59

Also Published As

Publication number Publication date
US20200356845A1 (en) 2020-11-12
EP3736742A1 (de) 2020-11-11
DE102019206621A1 (de) 2020-11-12
KR20200130153A (ko) 2020-11-18
CN111914990A (zh) 2020-11-10
US11790218B2 (en) 2023-10-17
CN111914990B (zh) 2025-08-15
EP3736742B1 (de) 2025-01-29
JP2020184341A (ja) 2020-11-12

Similar Documents

Publication Publication Date Title
CN120765532B (zh) 一种基于机器视觉的电阻片缺陷在线检测系统及分级方法
KR102877638B1 (ko) 뉴럴 네트워크 양자화를 위한 방법 및 장치
TWI837388B (zh) 用於深度神經網路中的深度優先迴旋的方法、設備及媒體
US12131103B2 (en) Semiconductor fabrication process parameter determination using a generative adversarial network
JP2020184341A (ja) 機械学習システム、並びに、機械学習システムを構成する方法、コンピュータプログラム及び装置
US20200183834A1 (en) Method and device for determining memory size
CN115690170A (zh) 一种针对不同尺度目标自适应的光流估计的方法及系统
JP2024045070A (ja) ロングテール分類用のマルチ教師グループ蒸留のためのシステム及び方法
CN118192447B (zh) 一种面向智能制造加工过程中的控制优化方法和系统
CN109388135A (zh) 使用深度时空学习的自主操作
US12400111B2 (en) Compressing a deep neural network
US20220327390A1 (en) Method for training a neural network
US12288156B2 (en) Machine learning system and a method, a computer program and a device for creating the machine learning system
CN115552482B (zh) 生成带不变积分层的卷积神经网络用于对象分类的方法
CN112182976B (zh) 一种工业设备剩余寿命预测方法
US12548314B2 (en) Method and device for training a neural network
WO2020083473A1 (en) System and method for a quantized neural network
US12353983B2 (en) Inference device and method for reducing the memory usage in a weight matrix
CN112292663A (zh) 使至少两个被乘数相乘的计算单元、方法和计算机程序
JP2018055570A (ja) 演算処理装置、演算処理方法及びプログラム
US20220067517A1 (en) Artificial neural network
CN111936942B (zh) 用于控制执行器的方法、计算机系统和计算机程序
KR20230068823A (ko) 인공 신경망 모델을 구동하기 위한 연산 방법 및 연산 장치
KR20210073769A (ko) 분산 클라우드 환경에서의 뉴럴 네트워크 파라미터 처리 방법 및 장치
US20260065659A1 (en) Method for processing sensor data, object detection network, and method for adapting an object detection network

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20230206

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230821

A871 Explanation of circumstances concerning accelerated examination

Free format text: JAPANESE INTERMEDIATE CODE: A871

Effective date: 20230821

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20231127

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20240226

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20240514

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20240521

R150 Certificate of patent or registration of utility model

Ref document number: 7493380

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150