JP2019164793A5 - - Google Patents

Download PDF

Info

Publication number
JP2019164793A5
JP2019164793A5 JP2019051636A JP2019051636A JP2019164793A5 JP 2019164793 A5 JP2019164793 A5 JP 2019164793A5 JP 2019051636 A JP2019051636 A JP 2019051636A JP 2019051636 A JP2019051636 A JP 2019051636A JP 2019164793 A5 JP2019164793 A5 JP 2019164793A5
Authority
JP
Japan
Prior art keywords
weights
layer
dnn
bit precision
weight
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.)
Withdrawn
Application number
JP2019051636A
Other languages
English (en)
Japanese (ja)
Other versions
JP2019164793A (ja
Filing date
Publication date
Priority claimed from US16/133,446 external-priority patent/US11429862B2/en
Application filed filed Critical
Publication of JP2019164793A publication Critical patent/JP2019164793A/ja
Publication of JP2019164793A5 publication Critical patent/JP2019164793A5/ja
Priority to JP2022001150A priority Critical patent/JP2022066192A/ja
Priority to JP2024009579A priority patent/JP7725628B2/ja
Withdrawn legal-status Critical Current

Links

JP2019051636A 2018-03-19 2019-03-19 ディープニューラルネットワークの動的適応 Withdrawn JP2019164793A (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
JP2022001150A JP2022066192A (ja) 2018-03-19 2022-01-06 ディープニューラルネットワークの動的適応
JP2024009579A JP7725628B2 (ja) 2018-03-19 2024-01-25 ディープニューラルネットワークの動的適応

Applications Claiming Priority (6)

Application Number Priority Date Filing Date Title
US201862644715P 2018-03-19 2018-03-19
US62/644,715 2018-03-19
US201862645358P 2018-03-20 2018-03-20
US62/645,358 2018-03-20
US16/133,446 US11429862B2 (en) 2018-03-20 2018-09-17 Dynamic adaptation of deep neural networks
US16/133,446 2018-09-17

Related Child Applications (1)

Application Number Title Priority Date Filing Date
JP2022001150A Division JP2022066192A (ja) 2018-03-19 2022-01-06 ディープニューラルネットワークの動的適応

Publications (2)

Publication Number Publication Date
JP2019164793A JP2019164793A (ja) 2019-09-26
JP2019164793A5 true JP2019164793A5 (enExample) 2020-11-26

Family

ID=65904040

Family Applications (3)

Application Number Title Priority Date Filing Date
JP2019051636A Withdrawn JP2019164793A (ja) 2018-03-19 2019-03-19 ディープニューラルネットワークの動的適応
JP2022001150A Withdrawn JP2022066192A (ja) 2018-03-19 2022-01-06 ディープニューラルネットワークの動的適応
JP2024009579A Active JP7725628B2 (ja) 2018-03-19 2024-01-25 ディープニューラルネットワークの動的適応

Family Applications After (2)

Application Number Title Priority Date Filing Date
JP2022001150A Withdrawn JP2022066192A (ja) 2018-03-19 2022-01-06 ディープニューラルネットワークの動的適応
JP2024009579A Active JP7725628B2 (ja) 2018-03-19 2024-01-25 ディープニューラルネットワークの動的適応

Country Status (3)

Country Link
EP (1) EP3543917B1 (enExample)
JP (3) JP2019164793A (enExample)
KR (1) KR102329590B1 (enExample)

Families Citing this family (88)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018176000A1 (en) 2017-03-23 2018-09-27 DeepScale, Inc. Data synthesis for autonomous control systems
US11893393B2 (en) 2017-07-24 2024-02-06 Tesla, Inc. Computational array microprocessor system with hardware arbiter managing memory requests
US11157441B2 (en) 2017-07-24 2021-10-26 Tesla, Inc. Computational array microprocessor system using non-consecutive data formatting
US10671349B2 (en) 2017-07-24 2020-06-02 Tesla, Inc. Accelerated mathematical engine
US11409692B2 (en) 2017-07-24 2022-08-09 Tesla, Inc. Vector computational unit
US12307350B2 (en) 2018-01-04 2025-05-20 Tesla, Inc. Systems and methods for hardware-based pooling
US11561791B2 (en) 2018-02-01 2023-01-24 Tesla, Inc. Vector computational unit receiving data elements in parallel from a last row of a computational array
EP3543917B1 (en) * 2018-03-19 2024-01-03 SRI International Inc. Dynamic adaptation of deep neural networks
US11429862B2 (en) 2018-03-20 2022-08-30 Sri International Dynamic adaptation of deep neural networks
US11215999B2 (en) 2018-06-20 2022-01-04 Tesla, Inc. Data pipeline and deep learning system for autonomous driving
CN108985920A (zh) 2018-06-22 2018-12-11 阿里巴巴集团控股有限公司 套现识别方法和装置
US11361457B2 (en) 2018-07-20 2022-06-14 Tesla, Inc. Annotation cross-labeling for autonomous control systems
US11636333B2 (en) 2018-07-26 2023-04-25 Tesla, Inc. Optimizing neural network structures for embedded systems
US11562231B2 (en) 2018-09-03 2023-01-24 Tesla, Inc. Neural networks for embedded devices
EP4664422A2 (en) 2018-10-11 2025-12-17 Tesla, Inc. Systems and methods for training machine models with augmented data
US11196678B2 (en) 2018-10-25 2021-12-07 Tesla, Inc. QOS manager for system on a chip communications
CA3114632A1 (en) * 2018-11-19 2020-05-28 Deeplite Inc. System and method for automated design space determination for deep neural networks
US11816585B2 (en) 2018-12-03 2023-11-14 Tesla, Inc. Machine learning models operating at different frequencies for autonomous vehicles
US11537811B2 (en) 2018-12-04 2022-12-27 Tesla, Inc. Enhanced object detection for autonomous vehicles based on field view
US11610117B2 (en) 2018-12-27 2023-03-21 Tesla, Inc. System and method for adapting a neural network model on a hardware platform
US10997461B2 (en) 2019-02-01 2021-05-04 Tesla, Inc. Generating ground truth for machine learning from time series elements
US11150664B2 (en) 2019-02-01 2021-10-19 Tesla, Inc. Predicting three-dimensional features for autonomous driving
US11567514B2 (en) 2019-02-11 2023-01-31 Tesla, Inc. Autonomous and user controlled vehicle summon to a target
US10956755B2 (en) 2019-02-19 2021-03-23 Tesla, Inc. Estimating object properties using visual image data
US11657118B2 (en) * 2019-05-23 2023-05-23 Google Llc Systems and methods for learning effective loss functions efficiently
CN112668362B (zh) * 2019-10-15 2023-06-16 浙江中正智能科技有限公司 一种动态优化类代理的人证比对模型训练方法
EP4047531A4 (en) * 2019-10-17 2022-10-26 Fujitsu Limited MACHINE LEARNING PROGRAM, MACHINE LEARNING METHOD AND MACHINE LEARNING DEVICE
US11775611B2 (en) 2019-11-01 2023-10-03 Samsung Electronics Co., Ltd. Piecewise quantization for neural networks
CN111079523B (zh) * 2019-11-05 2024-05-14 北京迈格威科技有限公司 物体检测方法、装置、计算机设备和存储介质
CN112784954B (zh) * 2019-11-08 2025-07-29 华为技术有限公司 确定神经网络的方法和装置
US11836490B2 (en) * 2019-11-14 2023-12-05 Nvidia Corporation Kernel coefficient quantization
US12039430B2 (en) * 2019-11-15 2024-07-16 Samsung Electronics Co., Ltd. Electronic device and method for inference binary and ternary neural networks
CN110942094B (zh) * 2019-11-26 2022-04-01 电子科技大学 一种基于范数的对抗性样本检测分类方法
KR102093080B1 (ko) * 2019-12-06 2020-04-27 주식회사 애자일소다 레이블 데이터 및 비레이블 데이터를 이용한 생성적 적대 신경망 기반의 분류 시스템 및 방법
US12019711B2 (en) 2019-12-06 2024-06-25 Agilesoda Inc. Classification system and method based on generative adversarial network
CN112926174B (zh) * 2019-12-06 2024-07-09 富益成科技有限公司 电池智能分流的控制方法及系统
US11899765B2 (en) 2019-12-23 2024-02-13 Dts Inc. Dual-factor identification system and method with adaptive enrollment
US11551145B2 (en) 2020-02-05 2023-01-10 International Business Machines Corporation Performance based switching of a model training process
US20230048206A1 (en) * 2020-02-06 2023-02-16 Hewlett-Packard Development Company, L.P. Controlling machine learning model structures
CN111399933B (zh) * 2020-02-11 2022-05-31 福建师范大学 一种边缘-云混合计算环境下的dnn任务卸载方法及终端
JP7268069B2 (ja) 2020-02-21 2023-05-02 アクタピオ,インコーポレイテッド 学習装置、学習方法、学習プログラム、評価装置、評価方法、および評価プログラム
US11586932B2 (en) 2020-03-10 2023-02-21 International Business Machines Corporation Model training with variable batch sizing and gradient checkpoint segments
CN111401430B (zh) * 2020-03-12 2022-04-01 四川大学 一种基于双通道深度神经网络的图像在线分类方法
US20230093630A1 (en) * 2020-03-17 2023-03-23 Interdigital Ce Patent Holdings System and method for adapting to changing constraints
KR102488281B1 (ko) * 2020-03-30 2023-01-13 주식회사 모빌린트 인공신경망의 활성값 및 가중값의 정밀도를 적응적으로 제어하는 방법 및 그 장치
CN113688851B (zh) * 2020-05-18 2023-09-15 华为云计算技术有限公司 数据标注方法和装置和精细粒度识别方法和装置
US12015526B2 (en) * 2020-05-26 2024-06-18 Synopsys, Inc. Mixed-precision neural networks
KR102831990B1 (ko) * 2020-06-11 2025-07-10 울산과학기술원 이기종 그래픽 프로세서 유닛 클러스터를 이용한 마이크로서비스 기반의 트레이닝 시스템 및 그 동작 방법
CN111738419B (zh) * 2020-06-19 2024-01-12 北京百度网讯科技有限公司 神经网络模型的量化方法和装置
CN111783957B (zh) * 2020-07-02 2024-05-03 厦门美图之家科技有限公司 模型量化训练方法、装置、机器可读存储介质及电子设备
CN111831354B (zh) * 2020-07-09 2023-05-16 北京灵汐科技有限公司 数据精度配置方法、装置、芯片、芯片阵列、设备及介质
JP6992864B1 (ja) 2020-09-28 2022-01-13 沖電気工業株式会社 ニューラルネットワーク軽量化装置、ニューラルネットワーク軽量化方法およびプログラム
US20220101133A1 (en) * 2020-09-29 2022-03-31 Qualcomm Incorporated Dynamic quantization for energy efficient deep learning
WO2022081260A1 (en) 2020-10-16 2022-04-21 Starkey Laboratories, Inc. Hearing device with dynamic neural networks for sound enhancement
US12488249B2 (en) 2020-10-20 2025-12-02 Samsung Electronics Co., Ltd. Secure, accurate and fast neural network inference by replacing at least one non-linear activation channel
CN114501353B (zh) * 2020-10-23 2024-01-05 维沃移动通信有限公司 通信信息的发送、接收方法及通信设备
CN112311488A (zh) * 2020-11-05 2021-02-02 上海应用技术大学 基于小波分解的频谱感知方法
US12159238B2 (en) 2020-12-10 2024-12-03 International Business Machines Corporation Automated machine learning model selection
GB2602294B (en) * 2020-12-22 2024-05-29 Imagination Tech Ltd Compressing a set of coefficients for subsequent use in a neural network
CN114492758B (zh) * 2021-02-05 2025-11-04 谷歌有限责任公司 使用逐层损失来训练神经网络
KR102314864B1 (ko) * 2021-03-29 2021-10-19 주식회사 리트빅 차량운전 상태정보를 이용한 에지 딥러닝 기반의 차량 안전운전 시스템
KR20220147398A (ko) * 2021-04-27 2022-11-03 삼성전자주식회사 인공 지능 모델에 기반하여 데이터를 처리하는 전자 장치 및 그 동작 방법
JP7187065B1 (ja) 2021-06-25 2022-12-12 株式会社モルフォ 計算手法決定システム、計算手法決定方法、及び、計算手法決定プログラム
CN113761787B (zh) * 2021-07-19 2024-08-02 中南大学 基于深度迁移网络的高炉铁水硅含量在线预测方法及系统
US12462575B2 (en) 2021-08-19 2025-11-04 Tesla, Inc. Vision-based machine learning model for autonomous driving with adjustable virtual camera
KR102590993B1 (ko) * 2021-09-03 2023-10-19 한국전자기술연구원 적응형 배치 프로세싱 방법 및 시스템
CN113872873B (zh) * 2021-09-29 2023-05-02 西安交通大学 一种适合5g新应用的多场景跨层拥塞控制方法
CN114037055A (zh) * 2021-11-05 2022-02-11 北京市商汤科技开发有限公司 数据处理系统、方法、装置、设备及存储介质
CN114118384B (zh) * 2021-12-09 2024-06-04 安谋科技(中国)有限公司 神经网络模型的量化方法、可读介质和电子设备
JPWO2023120205A1 (enExample) 2021-12-24 2023-06-29
US20250159177A1 (en) * 2022-02-18 2025-05-15 Intellectual Discovery Co., Ltd. Feature map compression method and apparatus
KR20240152306A (ko) * 2022-02-28 2024-10-21 퀄컴 인코포레이티드 멀티프로세서 컴퓨팅 디바이스에서 머신 러닝 동작들을 실행하기 위한 적응적 스케줄링
CN114861654B (zh) * 2022-03-31 2025-02-14 合肥伴学虎科技有限公司 一种中文文本中基于词性融合的对抗训练的防御方法
WO2023184359A1 (en) * 2022-03-31 2023-10-05 Qualcomm Incorporated System and method for image processing using mixed inference precision
CN115131858B (zh) * 2022-06-27 2025-11-18 合肥的卢深视科技有限公司 模型训练方法、人脸识别方法、电子设备及存储介质
WO2024063524A1 (ko) * 2022-09-21 2024-03-28 엘지전자 주식회사 무선 통신 시스템에서 온라인 학습을 수행하기 위한 장치 및 방법
CN116451824B (zh) * 2022-12-16 2024-08-20 西北工业大学 一种基于神经网络和蜜罐优化的光伏功率预测方法
WO2024155015A1 (ko) * 2023-01-18 2024-07-25 삼성전자 주식회사 영상 복호화 방법 및 장치, 및 영상 부호화 방법 및 장치
CN116381536B (zh) * 2023-03-07 2024-03-19 华中科技大学 一种基于回归元学习的锂电池健康状态预测的方法及系统
CN116129249B (zh) * 2023-04-04 2023-07-07 上海燧原科技有限公司 一种图像处理方法、装置、电子设备和存储介质
CN121195482A (zh) 2023-05-11 2025-12-23 欧摩威德国有限公司 用于无线电接入网络的高级模型适配的方法
CN116451757B (zh) * 2023-06-19 2023-09-08 山东浪潮科学研究院有限公司 一种神经网络模型的异构加速方法、装置、设备及介质
CN117033733B (zh) * 2023-10-09 2023-12-22 北京民谐文化传播有限公司 图书馆资源的智能自动分类与标签生成系统及方法
CN118196514B (zh) * 2024-03-25 2024-10-01 东营市人民医院 医疗影像识别模型生成方法及系统
CN119004468B (zh) * 2024-10-24 2025-02-11 浙江君同智能科技有限责任公司 基于生成对抗网络数据解耦的数据平衡去毒方法
CN119741543B (zh) * 2024-12-10 2025-12-02 重庆邮电大学 一种用于物联网cnn推理的双支路模型训练方法
CN120277469B (zh) * 2025-04-01 2025-08-22 西北大学 一种基于参数融合的地层总有机碳预测方法
CN120454204B (zh) * 2025-07-01 2025-09-19 南京德睿特来电能源研究院有限公司 虚拟电厂功率控制方法、装置、设备及存储介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0451386A (ja) * 1990-06-19 1992-02-19 Canon Inc ニューラルネットワーク及びその構築方法
JPH0628323A (ja) * 1992-07-06 1994-02-04 Nippon Telegr & Teleph Corp <Ntt> プロセス実行制御方法
US20150242741A1 (en) * 2014-02-21 2015-08-27 Qualcomm Incorporated In situ neural network co-processing
US11106973B2 (en) * 2016-03-16 2021-08-31 Hong Kong Applied Science and Technology Research Institute Company Limited Method and system for bit-depth reduction in artificial neural networks
GB201607713D0 (en) * 2016-05-03 2016-06-15 Imagination Tech Ltd Convolutional neural network
EP3543917B1 (en) * 2018-03-19 2024-01-03 SRI International Inc. Dynamic adaptation of deep neural networks

Similar Documents

Publication Publication Date Title
JP2019164793A5 (enExample)
EP3474194B1 (en) Method and apparatus with neural network parameter quantization
US11842178B2 (en) Compiler-level general matrix multiplication configuration optimization
US20230237375A1 (en) Dynamic placement of computation sub-graphs
CN110008952B (zh) 一种目标识别方法及设备
KR20160143505A (ko) 신경망의 연산량을 줄이는 방법 및 시스템
CN114127741B (zh) 用于人工智能建模的动态多层执行
US11120333B2 (en) Optimization of model generation in deep learning neural networks using smarter gradient descent calibration
CN113657595B (zh) 基于神经网络实时剪枝的神经网络加速器
JP2019079535A (ja) パラメータ処理方法及び装置
Billups et al. Derivative-free optimization of expensive functions with computational error using weighted regression
KR20200004700A (ko) 뉴럴 네트워크에서 파라미터를 처리하는 방법 및 장치
KR20190093932A (ko) 딥러닝 시스템에서의 연산 처리 장치 및 방법
US11620525B2 (en) Dropout for accelerated deep learning in heterogeneous architectures
CN114462591A (zh) 一种动态量化神经网络的推理方法
US20240144017A1 (en) Quantization range estimation for quantized training
WO2022196739A1 (ja) 求解装置およびプログラム
US11410036B2 (en) Arithmetic processing apparatus, control method, and non-transitory computer-readable recording medium having stored therein control program
KR20230012790A (ko) 함수 최적화 방법 및 장치
WO2022137520A1 (ja) 学習装置、学習方法および学習プログラム
CN116157808B (zh) 用于神经网络的组平衡式稀疏激活和联合激活权重稀疏训练的系统和方法
US20210216867A1 (en) Information processing apparatus, neural network computation program, and neural network computation method
CN120188170A (zh) 机器学习模型的硬件感知生成
KR20230137356A (ko) 계층적 및 공유 지수 부동 소수점 데이터 타입
Huang et al. Structured precision skipping: Accelerating convolutional neural networks with budget-aware dynamic precision selection