JP2020184341A5 - - Google Patents

Download PDF

Info

Publication number
JP2020184341A5
JP2020184341A5 JP2020081985A JP2020081985A JP2020184341A5 JP 2020184341 A5 JP2020184341 A5 JP 2020184341A5 JP 2020081985 A JP2020081985 A JP 2020081985A JP 2020081985 A JP2020081985 A JP 2020081985A JP 2020184341 A5 JP2020184341 A5 JP 2020184341A5
Authority
JP
Japan
Prior art keywords
machine learning
learning system
filter
images
variable
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.)
Granted
Application number
JP2020081985A
Other languages
English (en)
Japanese (ja)
Other versions
JP2020184341A (ja
JP7493380B2 (ja
Filing date
Publication date
Priority claimed from DE102019206621.6A external-priority patent/DE102019206621A1/de
Application filed filed Critical
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

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

Publications (3)

Publication Number Publication Date
JP2020184341A JP2020184341A (ja) 2020-11-12
JP2020184341A5 true JP2020184341A5 (https=) 2023-08-29
JP7493380B2 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 (https=)
EP (1) EP3736742B1 (https=)
JP (1) JP7493380B2 (https=)
KR (1) KR20200130153A (https=)
CN (1) CN111914990B (https=)
DE (1) DE102019206621A1 (https=)

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
US20220309320A1 (en) * 2021-03-25 2022-09-29 Smart Engines Service, LLC Almost-indirect convolution in quantized neural networks

Similar Documents

Publication Publication Date Title
CN113361698B (zh) 神经网络模型的处理方法和装置、数据处理方法和装置
JP2020184341A5 (https=)
KR102214837B1 (ko) 컨벌루션 신경망 파라미터 최적화 방법, 컨벌루션 신경망 연산방법 및 그 장치
CN111226234B (zh) 用于创建深度神经网络的方法、设备和计算机程序
KR20190118387A (ko) 합성곱 신경망 기반 이미지 처리 시스템 및 방법
JP2022518646A5 (https=)
JP2018160086A (ja) 畳込みニューラルネットワークによる処理方法、畳込みニューラルネットワークの学習方法、および畳込みニューラルネットワークを備える処理装置
CN110874636A (zh) 一种神经网络模型压缩方法、装置和计算机设备
WO2018216207A1 (ja) 画像処理装置、画像処理方法、および画像処理プログラム
KR20160131071A (ko) 신경망 및 신경망 트레이닝의 방법
CN105787867B (zh) 基于神经网络算法的处理视频图像的方法和装置
KR101987475B1 (ko) 하드웨어 구현에 적합한 신경망 파라미터 최적화 방법, 신경망 연산방법 및 그 장치
US12050976B2 (en) Convolution operations utilizing nonzero padding data copied from input channel data
WO2019006088A1 (en) LEARNING OF ARTIFICIAL NEURAL NETWORKS WITH REDUCED COMPLEXITY OF CALCULATION
KR102393761B1 (ko) 이미지 처리를 위한 인공 신경망 모델 학습 방법 및 시스템
KR102153192B1 (ko) 시뮬레이션-가이드된 반복적 프루닝을 사용하는 효율적인 네트워크 압축
KR20200132304A (ko) 영상 처리 장치 및 그 동작방법
CN109685805A (zh) 一种图像分割方法及装置
KR20230059457A (ko) 다중 태스크를 처리하는 프로세싱 장치
CN111161175A (zh) 一种用于去除图像反射分量的方法及系统
CN117611821A (zh) 一种实例分割方法、装置、系统及存储介质
US12430557B2 (en) Effective network compression using simulation-guided iterative pruning
KR20200130153A (ko) 기계 학습 시스템, 그리고 기계 학습 시스템을 생성하기 위한 방법, 컴퓨터 프로그램 및 장치
TWI789042B (zh) 具有平均量化機制的神經網路建構方法及裝置
CN110502576A (zh) 数据整合方法、分布式计算节点及分布式深度学习训练系统