DE102017125256A1 - Suche nach einer neuronalen Architektur - Google Patents

Suche nach einer neuronalen Architektur Download PDF

Info

Publication number
DE102017125256A1
DE102017125256A1 DE102017125256.8A DE102017125256A DE102017125256A1 DE 102017125256 A1 DE102017125256 A1 DE 102017125256A1 DE 102017125256 A DE102017125256 A DE 102017125256A DE 102017125256 A1 DE102017125256 A1 DE 102017125256A1
Authority
DE
Germany
Prior art keywords
neural
network
output
layer
neural network
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
DE102017125256.8A
Other languages
German (de)
English (en)
Inventor
Barret Zoph
Quoc V. Le
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.)
Google LLC
Original Assignee
Google LLC
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 Google LLC filed Critical Google LLC
Publication of DE102017125256A1 publication Critical patent/DE102017125256A1/de
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
    • G06N3/08—Learning methods
    • G06N3/0985—Hyperparameter optimisation; Meta-learning; Learning-to-learn
    • 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G06N3/09—Supervised 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
    • G06N3/08—Learning methods
    • G06N3/092—Reinforcement 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
    • G06N3/08—Learning methods
    • G06N3/098—Distributed learning, e.g. federated learning

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Feedback Control In General (AREA)
  • Debugging And Monitoring (AREA)
DE102017125256.8A 2016-10-28 2017-10-27 Suche nach einer neuronalen Architektur Pending DE102017125256A1 (de)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201662414300P 2016-10-28 2016-10-28
US62/414,300 2016-10-28

Publications (1)

Publication Number Publication Date
DE102017125256A1 true DE102017125256A1 (de) 2018-05-03

Family

ID=60473590

Family Applications (2)

Application Number Title Priority Date Filing Date
DE102017125256.8A Pending DE102017125256A1 (de) 2016-10-28 2017-10-27 Suche nach einer neuronalen Architektur
DE202017106532.4U Active DE202017106532U1 (de) 2016-10-28 2017-10-27 Suche nach einer neuronalen Architektur

Family Applications After (1)

Application Number Title Priority Date Filing Date
DE202017106532.4U Active DE202017106532U1 (de) 2016-10-28 2017-10-27 Suche nach einer neuronalen Architektur

Country Status (6)

Country Link
US (3) US11030523B2 (https=)
JP (3) JP6817431B2 (https=)
KR (2) KR102386806B1 (https=)
CN (1) CN108021983A (https=)
DE (2) DE102017125256A1 (https=)
WO (1) WO2018081563A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021004741A1 (de) * 2019-07-10 2021-01-14 Robert Bosch Gmbh Robusteres training für künstliche neuronale netzwerke

Families Citing this family (86)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10565493B2 (en) * 2016-09-22 2020-02-18 Salesforce.Com, Inc. Pointer sentinel mixture architecture
WO2018081563A1 (en) 2016-10-28 2018-05-03 Google Llc Neural architecture search
EP3602316A4 (en) * 2017-03-24 2020-12-30 D5A1 Llc LEARNING COACH FOR AUTOMATIC LEARNING SYSTEM
US12014257B2 (en) * 2017-05-19 2024-06-18 Salesforce, Inc. Domain specific language for generation of recurrent neural network architectures
WO2019084560A1 (en) * 2017-10-27 2019-05-02 Google Llc SEARCH FOR NEURONAL ARCHITECTURES
US11741342B2 (en) * 2018-05-18 2023-08-29 Baidu Usa Llc Resource-efficient neural architects
CN111819580B (zh) * 2018-05-29 2025-01-14 谷歌有限责任公司 用于密集图像预测任务的神经架构搜索
WO2019232693A1 (en) * 2018-06-05 2019-12-12 Beijing Didi Infinity Technology And Development Co., Ltd. System and method for ride order dispatching
DE112019003910T5 (de) * 2018-08-03 2021-04-29 Sony Corporation Informationsverarbeitungsverfahren, informationsverarbeitungsvorrichtung und informationsverarbeitungsprogramm
US12086718B2 (en) 2018-08-07 2024-09-10 Amadeus S.A.S. Machine learning systems and methods for attributed sequences
CN110826686B (zh) * 2018-08-07 2024-09-06 艾玛迪斯简易股份公司 有属性序列的机器学习系统和方法
KR20200023238A (ko) 2018-08-23 2020-03-04 삼성전자주식회사 딥러닝 모델을 생성하는 방법 및 시스템
CN109255374A (zh) * 2018-08-27 2019-01-22 中共中央办公厅电子科技学院 一种基于密集卷积网络和多任务网络的美学属性评价方法
EP3617953A1 (en) * 2018-08-30 2020-03-04 Koninklijke Philips N.V. An adaptable neural network
CN109189973B (zh) * 2018-08-30 2021-07-30 清华大学 基于策略梯度的大规模图像检索方法及装置
US11334791B2 (en) * 2018-09-05 2022-05-17 Siemens Healthcare Gmbh Learning to search deep network architectures
CN109065076B (zh) * 2018-09-05 2020-11-27 深圳追一科技有限公司 音频标签的设置方法、装置、设备和存储介质
CN110889487A (zh) * 2018-09-10 2020-03-17 富士通株式会社 神经网络架构搜索装置和方法及计算机可读记录介质
KR102066009B1 (ko) * 2018-09-14 2020-01-14 가천대학교 산학협력단 순환신경망을 사용한 의료영상기기의 영상복원 시스템
EP3629246B1 (en) * 2018-09-27 2022-05-18 Swisscom AG Systems and methods for neural architecture search
US11645509B2 (en) * 2018-09-27 2023-05-09 Salesforce.Com, Inc. Continual neural network learning via explicit structure learning
US20200104715A1 (en) * 2018-09-28 2020-04-02 Xilinx, Inc. Training of neural networks by including implementation cost as an objective
US11604992B2 (en) 2018-11-02 2023-03-14 Microsoft Technology Licensing, Llc Probabilistic neural network architecture generation
CN111144561B (zh) * 2018-11-05 2023-05-02 杭州海康威视数字技术股份有限公司 一种神经网络模型确定方法及装置
US11775812B2 (en) 2018-11-30 2023-10-03 Samsung Electronics Co., Ltd. Multi-task based lifelong learning
CN109615073B (zh) * 2018-12-03 2021-06-04 郑州云海信息技术有限公司 一种神经网络模型的构建方法、设备以及存储介质
US11556778B2 (en) * 2018-12-07 2023-01-17 Microsoft Technology Licensing, Llc Automated generation of machine learning models
CN111325311B (zh) * 2018-12-14 2024-03-29 深圳云天励飞技术有限公司 用于图像识别的神经网络模型生成方法及相关设备
US11114103B2 (en) * 2018-12-28 2021-09-07 Alibaba Group Holding Limited Systems, methods, and computer-readable storage media for audio signal processing
US10789510B2 (en) * 2019-01-11 2020-09-29 Google Llc Dynamic minibatch sizes
CN120509449A (zh) * 2019-01-23 2025-08-19 谷歌有限责任公司 用于神经网络的复合模型缩放
US11790212B2 (en) * 2019-03-18 2023-10-17 Microsoft Technology Licensing, Llc Quantization-aware neural architecture search
US11630990B2 (en) 2019-03-19 2023-04-18 Cisco Technology, Inc. Systems and methods for auto machine learning and neural architecture search
US12050979B2 (en) 2019-03-19 2024-07-30 Cisco Technology, Inc. Budgeted neural network architecture search system and method
DE102019204136A1 (de) * 2019-03-26 2020-10-01 Robert Bosch Gmbh Verfahren und Vorrichtung für Training und Herstellung eines künstlichen neuronalen Netzes
DE102019205081A1 (de) * 2019-04-09 2020-10-15 Robert Bosch Gmbh Verfahren, Vorrichtung und Computerprogramm zum Betreiben eines tiefen neuronalen Netzes
CN110110861B (zh) * 2019-05-09 2021-11-26 北京市商汤科技开发有限公司 确定模型超参数及模型训练的方法和装置、存储介质
US12046025B2 (en) * 2019-05-23 2024-07-23 Google Llc Connection weight learning for guided architecture evolution
CN111684471A (zh) * 2019-05-31 2020-09-18 深圳市大疆创新科技有限公司 网络结构搜索的方法及装置、计算机存储介质和计算机程序产品
CN110288084A (zh) * 2019-06-06 2019-09-27 北京小米智能科技有限公司 超网络训练方法和装置
US11640539B2 (en) * 2019-07-08 2023-05-02 Vianai Systems, Inc. Techniques for visualizing the operation of neural networks using samples of training data
CN110490320B (zh) * 2019-07-30 2022-08-23 西北工业大学 基于预测机制和遗传算法融合的深度神经网络结构优化方法
US11443162B2 (en) * 2019-08-23 2022-09-13 Google Llc Resource constrained neural network architecture search
CN110428046B (zh) * 2019-08-28 2023-12-15 腾讯科技（深圳）有限公司 神经网络结构的获取方法及装置、存储介质
CN110598852A (zh) * 2019-08-29 2019-12-20 北京小米移动软件有限公司 子网络采样方法、构建超网络拓扑结构的方法及装置
CN110543944B (zh) * 2019-09-11 2022-08-02 北京百度网讯科技有限公司 神经网络结构搜索方法、装置、电子设备和介质
CN110598629B (zh) * 2019-09-11 2023-06-06 北京百度网讯科技有限公司 超网络的搜索空间构建方法、装置以及电子设备
EP4012630A4 (en) 2019-09-17 2022-11-23 Huawei Cloud Computing Technologies Co., Ltd. METHOD AND DEVICE FOR MODEL OPTIMIZATION, STORAGE MEDIA AND DEVICE
WO2021058663A1 (en) 2019-09-25 2021-04-01 Deepmind Technologies Limited Augmenting attention-based neural networks to selectively attend to past inputs
US12293298B2 (en) * 2019-11-04 2025-05-06 Baidu Usa Llc Reducing training times of deep neural networks through efficient hybrid parallelism
CN110956262A (zh) * 2019-11-12 2020-04-03 北京小米智能科技有限公司 超网络训练方法及装置、电子设备、存储介质
CN112884118A (zh) * 2019-11-30 2021-06-01 华为技术有限公司 神经网络的搜索方法、装置及设备
CN112990461B (zh) * 2019-12-16 2023-09-19 杭州海康威视数字技术股份有限公司 构建神经网络模型的方法、装置、计算机设备和存储介质
CN113128678B (zh) * 2020-01-15 2025-05-09 华为技术有限公司 神经网络的自适应搜索方法及装置
CA3165790A1 (en) * 2020-01-27 2021-08-05 Akkio, Inc. Methods and systems for dynamically generating a plurality of machine learning systems during processing of a user data set
CN115066690A (zh) * 2020-02-07 2022-09-16 谷歌有限责任公司 搜索归一化-激活层架构
US11521028B2 (en) 2020-04-10 2022-12-06 Toyota Research Institute, Inc. Meta-learning neural architecture search via graph networks on search space lattices
CN111516700A (zh) * 2020-05-11 2020-08-11 安徽大学 一种驾驶员分心细粒度监测方法和系统
CN113762327B (zh) 2020-06-05 2024-07-09 宏达国际电子股份有限公司 机器学习方法、机器学习系统以及非暂态电脑可读取媒体
WO2021248068A1 (en) * 2020-06-05 2021-12-09 Google Llc Machine learning algorithm search with symbolic programming
US11436498B2 (en) * 2020-06-09 2022-09-06 Toyota Research Institute, Inc. Neural architecture search system for generating a neural network architecture
CN113837374B (zh) * 2020-06-23 2026-01-02 中兴通讯股份有限公司 神经网络的生成方法、设备及计算机可读存储介质
CN111782398B (zh) * 2020-06-29 2024-12-13 上海商汤智能科技有限公司 数据处理的方法、装置、系统及相关设备
JP6885553B1 (ja) 2020-07-14 2021-06-16 エッジコーティックス ピーティーイー． リミテッド ハードウェアとニューラルアーキテクチャとの共同探索
DE102020208828A1 (de) * 2020-07-15 2022-01-20 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren und Vorrichtung zum Erstellen eines maschinellen Lernsystems
US20230328559A1 (en) * 2020-08-18 2023-10-12 Qualcomm Incorporated Reporting configurations for neural network-based processing at a ue
EP3975060A1 (en) * 2020-09-29 2022-03-30 Samsung Electronics Co., Ltd. Method and apparatus for analysing neural network performance
US20220101063A1 (en) * 2020-09-29 2022-03-31 Samsung Electronics Co., Ltd. Method and apparatus for analyzing neural network performance
WO2022072890A1 (en) * 2020-10-02 2022-04-07 Google Llc Neural architecture and hardware accelerator search
KR102264571B1 (ko) * 2020-10-30 2021-06-15 주식회사 애자일소다 계층 구조를 갖는 의사결정 에이전트
US20220180207A1 (en) * 2020-12-04 2022-06-09 Google Llc Automated Machine Learning for Time Series Prediction
US20220198260A1 (en) * 2020-12-22 2022-06-23 International Business Machines Corporation Multi-level multi-objective automated machine learning
US12498908B2 (en) 2021-01-26 2025-12-16 Akkio Inc. Methods and systems for automatically generating and executing computer code using a natural language description of a data manipulation to be performed on a data set
WO2022169521A1 (en) 2021-02-04 2022-08-11 Google Llc Systems and methods for progressive learning for machine-learned models to optimize training speed
CN115393662A (zh) * 2021-05-08 2022-11-25 Oppo广东移动通信有限公司 图像处理方法、装置、计算机设备及存储介质
US12003261B2 (en) 2021-05-12 2024-06-04 Analog Devices, Inc. Model architecture search and optimization for hardware
US12028188B2 (en) 2021-05-12 2024-07-02 Analog Devices, Inc. Digital predistortion with hybrid basis-function-based actuator and neural network
CN113469078B (zh) * 2021-07-07 2023-07-04 西安电子科技大学 基于自动设计长短时记忆网络的高光谱图像分类方法
DE212022000260U1 (de) 2021-07-28 2024-05-21 Google Llc Bewerten von Ausgabesequenzen unter Benutzen eines neuronalen autoregressiven Sprachmodell-Netzwerkes
DE102021208197A1 (de) * 2021-07-29 2023-02-02 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren und Vorrichtung zum Erstellen eines maschinellen Lernsystems
KR102610429B1 (ko) * 2021-09-13 2023-12-06 연세대학교 산학협력단 인공신경망과 연산 가속기 구조 통합 탐색 장치 및 방법
KR20230100914A (ko) 2021-12-29 2023-07-06 경희대학교 산학협력단 인공신경망 탐색 방법 및 이를 수행하기 위한 컴퓨팅 장치
US12346665B2 (en) 2022-02-14 2025-07-01 International Business Machines Corporation Neural architecture search of language models using knowledge distillation
KR20230152448A (ko) * 2022-04-27 2023-11-03 현대자동차주식회사 Enas를 적용한 소음 및 진동 데이터 기반 이상상태 진단을 위한 ai 진단모델 자동생성 방법
KR102782300B1 (ko) 2022-05-16 2025-03-17 주식회사 뷰노 생체 신호 분석 방법
CN118798312A (zh) * 2024-01-17 2024-10-18 中国移动通信有限公司研究院 对话生成模型的训练方法、对话生成方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6553357B2 (en) 1999-09-01 2003-04-22 Koninklijke Philips Electronics N.V. Method for improving neural network architectures using evolutionary algorithms
CN102402712B (zh) 2011-08-31 2014-03-05 山东大学 基于神经网络的机器人强化学习初始化方法
US10275719B2 (en) 2015-01-29 2019-04-30 Qualcomm Incorporated Hyper-parameter selection for deep convolutional networks
JP2017102906A (ja) 2015-11-25 2017-06-08 キヤノン株式会社 情報処理装置、情報処理方法及びプログラム
JP6470165B2 (ja) * 2015-12-15 2019-02-13 株式会社東芝 サーバ、システム及び探索方法
US9899672B2 (en) 2016-05-17 2018-02-20 Nanotek Instruments, Inc. Chemical-free production of graphene-encapsulated electrode active material particles for battery applications
WO2018081563A1 (en) 2016-10-28 2018-05-03 Google Llc Neural architecture search

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021004741A1 (de) * 2019-07-10 2021-01-14 Robert Bosch Gmbh Robusteres training für künstliche neuronale netzwerke

Also Published As

Publication number Publication date
JP2021064390A (ja) 2021-04-22
JP6817431B2 (ja) 2021-01-20
DE202017106532U1 (de) 2018-02-05
WO2018081563A1 (en) 2018-05-03
JP2023024993A (ja) 2023-02-21
KR20190052143A (ko) 2019-05-15
JP2019533257A (ja) 2019-11-14
JP7516482B2 (ja) 2024-07-16
CN108021983A (zh) 2018-05-11
JP7210531B2 (ja) 2023-01-23
US20210295163A1 (en) 2021-09-23
KR20220047688A (ko) 2022-04-18
US11030523B2 (en) 2021-06-08
KR102386806B1 (ko) 2022-04-14
US20190251439A1 (en) 2019-08-15
US11829874B2 (en) 2023-11-28
KR102532658B1 (ko) 2023-05-15
US20230368024A1 (en) 2023-11-16
WO2018081563A9 (en) 2019-03-07

Similar Documents

Publication Publication Date Title
DE102017125256A1 (de) Suche nach einer neuronalen Architektur
DE102016125838B4 (de) Komprimierte rekurrente neuronale netzmodelle
DE112022000106B4 (de) Verfahren und Vorrichtung zur Getriebefehlerdiagnose und Signalerfassung sowie elektronisches Gerät
DE202023003086U1 (de) Erweiterung von Maschinenlernsprachmodellen unter Verwendung von Suchmaschinenergebnissen
DE212022000260U1 (de) Bewerten von Ausgabesequenzen unter Benutzen eines neuronalen autoregressiven Sprachmodell-Netzwerkes
DE202017106363U1 (de) Neuronale Antwort-auf-Frage-Netze
DE102019004300A1 (de) Verwendung eines dynamischen speichernetzwerks zum verfolgen digitaler dialogzustände und erzeugen von antworten
DE102023124207A1 (de) Einzelbild-Konzept-Kodierer zur Personalisierung unter Verwendung eines vortrainierten Diffusionsmodells
DE202017007641U1 (de) Training von maschinellen Lernmodellen auf mehrere maschinelle Lernaufgaben
DE102021004562A1 (de) Abwandlung von Szenengraphen auf Grundlage von Befehlen in natürlicher Sprache
DE102018009243A1 (de) Abstrahierendes Zusammenfassen langer Dokumente unter Nutzung des Deep-Learning strukturierter Dokumente
DE102016125918A1 (de) Komprimierte rekurrente neuronale Netzwerkmodelle
DE202016004627U1 (de) Training eines neuronalen Wertnetzwerks
DE202017107393U1 (de) Vorhersagen eines Suchmaschinen-Einordnungssignalwerts
DE112016000509T5 (de) Batch-Normalisierungsschichten
DE112020000227T5 (de) Maschinelles lernen eines computermodells auf grundlage von korrelationenvon trainingsdaten mit leistungstrends
DE202016004628U1 (de) Durchqueren einer Umgebungsstatusstruktur unter Verwendung neuronaler Netze
DE202018101275U1 (de) Tiefenverkettung unter Verwendung einer Matrixberechnungseinheit
DE102016013372A1 (de) Bildbeschriften mit schwacher Überwachung
DE112020003050T5 (de) Fehlerkompensation in analogen neuronalen netzen
DE112023002024T5 (de) Datenschutzsensibles trainieren von neuronalen netzen unter verwendung von datenerweiterung
DE112021003506T5 (de) Hybrides ensemble-modell, das edge- und serverseitige inferenzen nutzt
DE112024002110T5 (de) Erkennung von durch künstliche intelligenz erzeugtem text
DE102024205216A1 (de) Einschritt-Diffusionsdestillation über tiefe Gleichgewichtsmodelle
DE202024105837U1 (de) Effizientes Wissensdestillations-Framework zum Trainieren maschinell erlernter Modelle

Legal Events

Date Code Title Description
R012 Request for examination validly filed
R016 Response to examination communication
R016 Response to examination communication