JP7344900B2 - 教師付き機械学習問題用のニューラルネットワークアーキテクチャの選択 - Google Patents

教師付き機械学習問題用のニューラルネットワークアーキテクチャの選択 Download PDF

Info

Publication number
JP7344900B2
JP7344900B2 JP2020555022A JP2020555022A JP7344900B2 JP 7344900 B2 JP7344900 B2 JP 7344900B2 JP 2020555022 A JP2020555022 A JP 2020555022A JP 2020555022 A JP2020555022 A JP 2020555022A JP 7344900 B2 JP7344900 B2 JP 7344900B2
Authority
JP
Japan
Prior art keywords
neural network
measure
machine learning
candidate neural
learning problem
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.)
Active
Application number
JP2020555022A
Other languages
English (en)
Japanese (ja)
Other versions
JP2021523430A5 (enExample
JP2021523430A (ja
Inventor
アミザデ，サイード
ヤン，ゲ
フシ，ニコロ
パオロ カザーレ，フランチェスコ
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.)
Microsoft Technology Licensing LLC
Original Assignee
Microsoft Technology Licensing 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 Microsoft Technology Licensing LLC filed Critical Microsoft Technology Licensing LLC
Publication of JP2021523430A publication Critical patent/JP2021523430A/ja
Publication of JP2021523430A5 publication Critical patent/JP2021523430A5/ja
Application granted granted Critical
Publication of JP7344900B2 publication Critical patent/JP7344900B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06N3/04—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
    • G06N3/04—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
    • G06N3/045—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
    • G06N3/047—Probabilistic or stochastic 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
    • G06N3/0499—Feedforward 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
    • G06N3/08—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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Probability & Statistics with Applications (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Complex Calculations (AREA)
  • Image Analysis (AREA)
  • Debugging And Monitoring (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
JP2020555022A 2018-05-10 2019-04-27 教師付き機械学習問題用のニューラルネットワークアーキテクチャの選択 Active JP7344900B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US15/976,514 2018-05-10
US15/976,514 US11995538B2 (en) 2018-05-10 2018-05-10 Selecting a neural network architecture for a supervised machine learning problem
PCT/US2019/029532 WO2019217113A1 (en) 2018-05-10 2019-04-27 Selecting a neural network architecture for a supervised machine learning problem

Publications (3)

Publication Number Publication Date
JP2021523430A JP2021523430A (ja) 2021-09-02
JP2021523430A5 JP2021523430A5 (enExample) 2022-04-06
JP7344900B2 true JP7344900B2 (ja) 2023-09-14

Family

ID=66429706

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2020555022A Active JP7344900B2 (ja) 2018-05-10 2019-04-27 教師付き機械学習問題用のニューラルネットワークアーキテクチャの選択

Country Status (6)

Country Link
US (3) US11995538B2 (enExample)
EP (1) EP3791326A1 (enExample)
JP (1) JP7344900B2 (enExample)
CN (2) CN120297334A (enExample)
CA (1) CA3097036A1 (enExample)
WO (1) WO2019217113A1 (enExample)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11196623B2 (en) 2016-12-30 2021-12-07 Intel Corporation Data packaging protocols for communications between IoT devices
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
US11537846B2 (en) * 2018-08-21 2022-12-27 Wisconsin Alumni Research Foundation Neural network architecture with concurrent uncertainty output
KR102200212B1 (ko) * 2018-12-07 2021-01-08 서울대학교 산학협력단 불확실성 예측을 위한 샘플링 모델 생성 장치 및 방법, 불확실성 예측 장치
US10616257B1 (en) * 2019-02-19 2020-04-07 Verizon Patent And Licensing Inc. Method and system for anomaly detection and network deployment based on quantitative assessment
US11240340B2 (en) * 2020-05-12 2022-02-01 International Business Machines Corporation Optimized deployment of analytic models in an edge topology
CN113807376A (zh) * 2020-06-15 2021-12-17 富泰华工业（深圳）有限公司 网络模型优化方法、装置、电子设备及存储介质
CN112134876A (zh) * 2020-09-18 2020-12-25 中移（杭州）信息技术有限公司 流量识别系统及方法、服务器
KR102535007B1 (ko) * 2020-11-13 2023-05-19 숭실대학교 산학협력단 Snn 모델 파라미터를 기반으로 모델 수행을 위한 뉴로모픽 아키텍처 동적 선택 방법, 이를 수행하기 위한 기록 매체 및 장치
US20220164646A1 (en) * 2020-11-24 2022-05-26 EMC IP Holding Company LLC Hydratable neural networks for devices
CN113204916B (zh) * 2021-04-15 2021-11-19 特斯联科技集团有限公司 基于强化学习的智能决策方法及系统
US20220027792A1 (en) * 2021-10-08 2022-01-27 Intel Corporation Deep neural network model design enhanced by real-time proxy evaluation feedback
US12367249B2 (en) * 2021-10-19 2025-07-22 Intel Corporation Framework for optimization of machine learning architectures
US12367248B2 (en) * 2021-10-19 2025-07-22 Intel Corporation Hardware-aware machine learning model search mechanisms
US12417260B2 (en) 2021-10-20 2025-09-16 Intel Corporation Machine learning model scaling system with energy efficient network data transfer for power aware hardware
CN114037058B (zh) * 2021-11-05 2024-05-17 北京百度网讯科技有限公司 预训练模型的生成方法、装置、电子设备以及存储介质
CN114188022A (zh) * 2021-12-13 2022-03-15 浙江大学 一种基于TextCNN模型的临床儿童咳嗽智能预诊断系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015533437A (ja) 2012-10-19 2015-11-24 アピシオ，インク． 識別不能化および再識別を用いた医療情報解析のためのシステムおよび方法
US20150339572A1 (en) 2014-05-23 2015-11-26 DataRobot, Inc. Systems and techniques for predictive data analytics
WO2017058489A1 (en) 2015-09-30 2017-04-06 Apple Inc. Methods for color and texture control of metallic glasses by the combination of blasting and oxidization

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05314090A (ja) 1992-05-14 1993-11-26 Hitachi Ltd ニューラルネットを用いたパターン認識方法およびその装置
JP2008533615A (ja) 2005-03-14 2008-08-21 エル ターラー、ステフエン ニューラルネットワーク開発およびデータ解析ツール
US9659248B1 (en) * 2016-01-19 2017-05-23 International Business Machines Corporation Machine learning and training a computer-implemented neural network to retrieve semantically equivalent questions using hybrid in-memory representations
WO2018075995A1 (en) 2016-10-21 2018-04-26 DataRobot, Inc. Systems for predictive data analytics, and related methods and apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015533437A (ja) 2012-10-19 2015-11-24 アピシオ，インク． 識別不能化および再識別を用いた医療情報解析のためのシステムおよび方法
US20150339572A1 (en) 2014-05-23 2015-11-26 DataRobot, Inc. Systems and techniques for predictive data analytics
JP2017520068A (ja) 2014-05-23 2017-07-20 データロボット， インコーポレイテッド 予測データ分析のためのシステムおよび技術
WO2017058489A1 (en) 2015-09-30 2017-04-06 Apple Inc. Methods for color and texture control of metallic glasses by the combination of blasting and oxidization

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Andrew Brock et al，SMASH: One-Shot Model Architecture Search through HyperNetworks，[online]，2017年08月17日，［検索日 ２０２３年３月２８日］、インターネット＜https://arxiv.org/abs/1708.05344＞
Philippe Hamel et al，TRANSFER LEARNING IN MIR: SMARING LEARNED LATENT REPRESENTATIONS FOR MUSIC AUDIO CLASSIFICATION AND SIMILARITY， [online]，2013年，［検索日 ２０２３年３月２８日］、インターネット＜https://archives.ismir.net/ismir2013/paper/000076.pdf＞
Thomas Elsken et al，SIMPLE AND EFFICIENT ARCHITECTURE SEARCH FOR CONVOLUTIONAL NEURAL NETWORKS， [online]，2017年11月13日，［検索日 ２０２３年３月２８日］、インターネット＜https://arxiv.org/abs/1711.04528＞

Also Published As

Publication number Publication date
US20190347548A1 (en) 2019-11-14
EP3791326A1 (en) 2021-03-17
CN120297334A (zh) 2025-07-11
US20250390745A1 (en) 2025-12-25
US20240273370A1 (en) 2024-08-15
CN112470171B (zh) 2025-04-18
US11995538B2 (en) 2024-05-28
CN112470171A (zh) 2021-03-09
CA3097036A1 (en) 2019-11-14
JP2021523430A (ja) 2021-09-02
KR20210008480A (ko) 2021-01-22
WO2019217113A1 (en) 2019-11-14
US12423581B2 (en) 2025-09-23

Similar Documents

Publication Publication Date Title
JP7344900B2 (ja) 教師付き機械学習問題用のニューラルネットワークアーキテクチャの選択
US11361225B2 (en) Neural network architecture for attention based efficient model adaptation
US11392859B2 (en) Large-scale automated hyperparameter tuning
EP3912056B1 (en) Leveraging query executions to improve index recommendations
US20210074016A1 (en) Hand pose estimation from stereo cameras
WO2022068623A1 (zh) 一种模型训练方法及相关设备
US20190385073A1 (en) Visual recognition via light weight neural network
US20210056434A1 (en) Model tree classifier system
CN113869496B (zh) 一种神经网络的获取方法、数据处理方法以及相关设备
US20170004159A1 (en) Search engine optimization by selective indexing
KR20240121445A (ko) 마르코프 전이 필드를 이용한 컨벌루션 신경망 모델 기반의 사용자 위치 측정 방법 및 이를 지원하는 장치
CN113065634B (zh) 一种图像处理方法、神经网络的训练方法以及相关设备
US20260105384A1 (en) Dynamically scalable machine learning model generation and retraining through containerization
CN117193859A (zh) 一种分支预测方法以及相关设备
KR102956712B1 (ko) 지도 머신 학습 문제를 위한 신경망 아키텍처 선택
CN113111996A (zh) 模型生成方法和装置
JP2025515985A (ja) 大規模イメージ基盤測位におけるデータ保存
US12519817B2 (en) Generative artificial intelligence penetration testing automation
US20250363417A1 (en) Computer architecture for predicting energy consumption of machine learning inference
KR20240121444A (ko) 잡음제거 오토인코더를 이용한 rssi 핑거프린팅 기반의 사용자 위치 측정 방법 및 이를 지원하는 장치
WO2026010723A1 (en) Trigger-based data ingestion for machine learning using edge device
WO2025245298A1 (en) Computer architecture for predicting energy consumption of machine learning inference

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220328

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20220328

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20230327

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20230404

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230630

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20230807

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20230904

R150 Certificate of patent or registration of utility model

Ref document number: 7344900

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150