DE102021205690A1 - Trainieren neuronaler Netze mit begrenzten Daten unter Verwendung invertierbarer Augmentationsoperatoren - Google Patents

Trainieren neuronaler Netze mit begrenzten Daten unter Verwendung invertierbarer Augmentationsoperatoren Download PDF

Info

Publication number
DE102021205690A1
DE102021205690A1 DE102021205690.3A DE102021205690A DE102021205690A1 DE 102021205690 A1 DE102021205690 A1 DE 102021205690A1 DE 102021205690 A DE102021205690 A DE 102021205690A DE 102021205690 A1 DE102021205690 A1 DE 102021205690A1
Authority
DE
Germany
Prior art keywords
data
augmentation
training
distribution
computer
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
DE102021205690.3A
Other languages
German (de)
English (en)
Inventor
Tero Tapani KARRAS
Miika Samuli Aittala
Janne Johannes Hellsten
Samuli Matias Laine
Jaakko T. Lehtinen
Timo Oskari Aila
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.)
Nvidia Corp
Original Assignee
Nvidia Corp
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
Priority claimed from US17/210,934 external-priority patent/US20210383241A1/en
Application filed by Nvidia Corp filed Critical Nvidia Corp
Publication of DE102021205690A1 publication Critical patent/DE102021205690A1/de
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Neurology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
DE102021205690.3A 2020-06-05 2021-06-04 Trainieren neuronaler Netze mit begrenzten Daten unter Verwendung invertierbarer Augmentationsoperatoren Pending DE102021205690A1 (de)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202063035448P 2020-06-05 2020-06-05
US63/035,448 2020-06-05
US17/210,934 2021-03-24
US17/210,934 US20210383241A1 (en) 2020-06-05 2021-03-24 Training neural networks with limited data using invertible augmentation operators

Publications (1)

Publication Number Publication Date
DE102021205690A1 true DE102021205690A1 (de) 2021-12-09

Family

ID=78605367

Family Applications (1)

Application Number Title Priority Date Filing Date
DE102021205690.3A Pending DE102021205690A1 (de) 2020-06-05 2021-06-04 Trainieren neuronaler Netze mit begrenzten Daten unter Verwendung invertierbarer Augmentationsoperatoren

Country Status (2)

Country Link
CN (1) CN113762461A (zh)
DE (1) DE102021205690A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116738911A (zh) * 2023-07-10 2023-09-12 苏州异格技术有限公司 布线拥塞预测方法、装置及计算机设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114338385B (zh) * 2021-12-31 2024-05-17 上海商汤智能科技有限公司 网络配置方法及系统、电子设备和存储介质
CN116248412B (zh) * 2023-04-27 2023-08-22 中国人民解放军总医院 共享数据资源异常检测方法、系统、设备、存储器及产品
CN116664566B (zh) * 2023-07-28 2023-09-26 成都数智创新精益科技有限公司 一种oled面板丝印质量控制方法及系统及装置及介质

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6778866B2 (ja) * 2015-03-31 2020-11-04 国立大学法人東北大学 磁気抵抗効果素子、磁気メモリ装置、製造方法、動作方法、及び集積回路
US10346740B2 (en) * 2016-06-01 2019-07-09 Kla-Tencor Corp. Systems and methods incorporating a neural network and a forward physical model for semiconductor applications
US11042811B2 (en) * 2016-10-05 2021-06-22 D-Wave Systems Inc. Discrete variational auto-encoder systems and methods for machine learning using adiabatic quantum computers
WO2018226492A1 (en) * 2017-06-05 2018-12-13 D5Ai Llc Asynchronous agents with learning coaches and structurally modifying deep neural networks without performance degradation
KR102416048B1 (ko) * 2017-10-16 2022-07-04 일루미나, 인코포레이티드 변이체 분류를 위한 심층 컨볼루션 신경망
CN111145106B (zh) * 2019-12-06 2023-03-10 深圳市雄帝科技股份有限公司 一种图像增强方法、装置、介质及设备

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116738911A (zh) * 2023-07-10 2023-09-12 苏州异格技术有限公司 布线拥塞预测方法、装置及计算机设备
CN116738911B (zh) * 2023-07-10 2024-04-30 苏州异格技术有限公司 布线拥塞预测方法、装置及计算机设备

Also Published As

Publication number Publication date
CN113762461A (zh) 2021-12-07

Similar Documents

Publication Publication Date Title
DE102018126670A1 (de) Fortschreitende Modifizierung von generativen adversativen neuronalen Netzen
DE102018132069A1 (de) Äquivariante Orientierungspunkt-Transformation für Orientierungspunkt-Lokalisierung
DE102021119726A1 (de) Dreidimensionale objektrekonstruktion aus einem video
DE102018117813A1 (de) Zeitlich stabile Datenrekonstruktion mit einem externen rekurrenten neuronalen Netzwerk
DE102019106123A1 (de) Dreidimensionale (3D) Posenschätzung von Seiten einer monokularen Kamera
DE102021205690A1 (de) Trainieren neuronaler Netze mit begrenzten Daten unter Verwendung invertierbarer Augmentationsoperatoren
DE112020004107T5 (de) Inhaltsempfehlungen unter verwendung eines oder mehrerer neuronaler netze
DE102021119722A1 (de) Feingranulare pro-vektor-skalierung für neuronale netzwerkquantisierung
DE102021121109A1 (de) Wiederherstellung dreidimensionaler modelle aus zweidimensionalen bildern
DE102021105249A1 (de) Mikrotraining zur iterativen verfeinerung eines neuronalen netzes mit wenigen anpassungen
DE102018124211A1 (de) Lernbasierte Kameraposenschätzung von Bildern einer Umgebung
DE102022100360A1 (de) Framework für maschinelles lernen angewandt bei einer halbüberwachten einstellung, um instanzenverfolgung in einer sequenz von bildframes durchzuführen
DE102022118651A1 (de) Mehrfachauflösung-hash-codierung für neuronale netzwerke
US20210383241A1 (en) Training neural networks with limited data using invertible augmentation operators
DE102022113244A1 (de) Gemeinsame Form- und Erscheinungsbildoptimierung durch Topologieabtastung
DE102018114799A1 (de) Halbüberwachtes lernen zur orientierungspunktlokalisierung
DE102021132992A1 (de) Messen und Detektieren von Leerlaufzeiten und Erkennen der Ursachen dafür in Cloud-basierten Streaming-Anwendungen
DE102021130031A1 (de) Erscheinungsbildgesteuerte automatische dreidimensionale modellierung
DE102022104142A1 (de) Strahldichte-caching in echtzeit durch ein neuronales netz für pfadverfolgungszwecke
DE102022123434A1 (de) Gemeinsame Schätzung von Herzfrequenz und Atemfrequenz unter Verwendung neuronaler Netze
DE102021109050A1 (de) Durch ein neuronales generative adversarial netzwerk unterstützte videokompression und -übertragung
DE102022121509A1 (de) Einzelbild-inversrendering
DE102023104326A1 (de) Hierarchisches netzwerk für gestapeltes speichersystem
DE102022107232A1 (de) Gepackter fehlerkorrekturcode (ecc) für komprimierten datenschutz
DE102022121649A1 (de) Schnelles Neutraining von vollständig fusionierten neuronalen Transceiver-Komponenten

Legal Events

Date Code Title Description
R012 Request for examination validly filed