KR20230083716A - 뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법 - Google Patents

뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법 Download PDF

Info

Publication number
KR20230083716A
KR20230083716A KR1020210171979A KR20210171979A KR20230083716A KR 20230083716 A KR20230083716 A KR 20230083716A KR 1020210171979 A KR1020210171979 A KR 1020210171979A KR 20210171979 A KR20210171979 A KR 20210171979A KR 20230083716 A KR20230083716 A KR 20230083716A
Authority
KR
South Korea
Prior art keywords
neural network
architecture
hardware resource
loss
candidate
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.)
Pending
Application number
KR1020210171979A
Other languages
English (en)
Korean (ko)
Inventor
이원희
Original Assignee
삼성전자주식회사
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 삼성전자주식회사 filed Critical 삼성전자주식회사
Priority to KR1020210171979A priority Critical patent/KR20230083716A/ko
Priority to US17/743,906 priority patent/US20230177308A1/en
Priority to CN202210663806.3A priority patent/CN116258183A/zh
Priority to JP2022129509A priority patent/JP2023083207A/ja
Priority to EP22193593.5A priority patent/EP4191481A1/en
Publication of KR20230083716A publication Critical patent/KR20230083716A/ko
Pending legal-status Critical Current

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
    • G06N3/06—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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/50—Adding; Subtracting
    • 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
    • G06N3/082—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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating 3D models or images for computer graphics
    • G06T19/006—Mixed reality
    • 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]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Neurology (AREA)
  • Computer Graphics (AREA)
  • Computer Hardware Design (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
KR1020210171979A 2021-12-03 2021-12-03 뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법 Pending KR20230083716A (ko)

Priority Applications (5)

Application Number Priority Date Filing Date Title
KR1020210171979A KR20230083716A (ko) 2021-12-03 2021-12-03 뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법
US17/743,906 US20230177308A1 (en) 2021-12-03 2022-05-13 Method and apparatus with neural network architecture search
CN202210663806.3A CN116258183A (zh) 2021-12-03 2022-06-13 用于神经网络架构搜索的方法和装置
JP2022129509A JP2023083207A (ja) 2021-12-03 2022-08-16 ニューラルネットワークの最適なアーキテクチャーを探索する装置及び方法
EP22193593.5A EP4191481A1 (en) 2021-12-03 2022-09-02 Method and apparatus with neural network architecture search

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020210171979A KR20230083716A (ko) 2021-12-03 2021-12-03 뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법

Publications (1)

Publication Number Publication Date
KR20230083716A true KR20230083716A (ko) 2023-06-12

Family

ID=83191939

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020210171979A Pending KR20230083716A (ko) 2021-12-03 2021-12-03 뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법

Country Status (5)

Country Link
US (1) US20230177308A1 (enExample)
EP (1) EP4191481A1 (enExample)
JP (1) JP2023083207A (enExample)
KR (1) KR20230083716A (enExample)
CN (1) CN116258183A (enExample)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12353992B2 (en) * 2018-10-01 2025-07-08 Google Llc Systems and methods for providing a machine-learned model with adjustable computational demand

Also Published As

Publication number Publication date
EP4191481A1 (en) 2023-06-07
JP2023083207A (ja) 2023-06-15
US20230177308A1 (en) 2023-06-08
CN116258183A (zh) 2023-06-13

Similar Documents

Publication Publication Date Title
EP3695281B1 (en) Autonomous driving apparatus and method thereof
CN112470171A (zh) 选择用于有监督机器学习问题的神经网络架构
US20210209468A1 (en) Learning device, inference device, method, and program
KR20200043169A (ko) 뉴럴 네트워크의 파라미터를 양자화하는 방법 및 장치
US20190220969A1 (en) Information processing device, data structure, information processing method, and non-transitory computer readable storage medium
KR102305613B1 (ko) 감정 인식 방법 및 장치
KR101828215B1 (ko) Long Short Term Memory 기반 순환형 상태 전이 모델의 학습 방법 및 장치
KR20250054046A (ko) 전자 장치 및 그의 제어 방법
KR20230081214A (ko) 뉴럴 네트워크의 분산 학습을 수행하는 학습 방법 및 이를 수행하는 학습 장치
US11430137B2 (en) Electronic device and control method therefor
KR20220094564A (ko) 딥러닝 모델 서빙 최적화를 위한 모델 자동 경량화 방법 및 장치, 이를 이용한 클라우드 추론 서비스 제공 방법
US20230289498A1 (en) Machine learning system for parameterizing building information from building images
KR102561799B1 (ko) 디바이스에서 딥러닝 모델의 레이턴시를 예측하는 방법 및 시스템
CN116897356A (zh) 算子的调度运行时间比较方法、装置及存储介质
KR20210045225A (ko) 뉴럴 네트워크에서 연산을 수행하는 방법 및 장치
US20200012920A1 (en) Method and apparatus for determining goodness of fit related to microphone placement
US11211045B2 (en) Artificial intelligence apparatus and method for predicting performance of voice recognition model in user environment
KR20210115863A (ko) 뉴럴 네트워크 모델을 위한 병렬 처리 방법 및 장치
KR20230083716A (ko) 뉴럴 네트워크의 최적의 아키텍쳐를 탐색하는 장치 및 방법
CN114091589A (zh) 模型训练方法、装置、电子设备及介质
CN117150285A (zh) 估计机器学习模型系统和应用的最佳训练数据集大小
KR20230071719A (ko) 이미지 처리용 신경망 훈련 방법 및 전자 장치
KR20230147908A (ko) 오픈 소스 라이선스를 검증하는 전자 장치 및 방법
US20250272551A1 (en) Activation-based quantization of machine learning model parameters
JP2023552048A (ja) ハードウェアアクセラレータのためのニューラルアーキテクチャスケーリング

Legal Events

Date Code Title Description
PA0109 Patent application

Patent event code: PA01091R01D

Comment text: Patent Application

Patent event date: 20211203

PG1501 Laying open of application
A201 Request for examination
PA0201 Request for examination

Patent event code: PA02012R01D

Patent event date: 20241107

Comment text: Request for Examination of Application