JP7162074B2 - 機械学習を行うための方法及びシステム - Google Patents

機械学習を行うための方法及びシステム Download PDF

Info

Publication number
JP7162074B2
JP7162074B2 JP2020558533A JP2020558533A JP7162074B2 JP 7162074 B2 JP7162074 B2 JP 7162074B2 JP 2020558533 A JP2020558533 A JP 2020558533A JP 2020558533 A JP2020558533 A JP 2020558533A JP 7162074 B2 JP7162074 B2 JP 7162074B2
Authority
JP
Japan
Prior art keywords
machine learning
learning model
layer
training data
connections
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
JP2020558533A
Other languages
English (en)
Japanese (ja)
Other versions
JP2021522574A5 (https=
JP2021522574A (ja
JPWO2019210237A5 (https=
Inventor
ハン，リャン
Original Assignee
アリババ グループ ホウルディング リミテッド
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 アリババ グループ ホウルディング リミテッド filed Critical アリババ グループ ホウルディング リミテッド
Publication of JP2021522574A publication Critical patent/JP2021522574A/ja
Publication of JP2021522574A5 publication Critical patent/JP2021522574A5/ja
Publication of JPWO2019210237A5 publication Critical patent/JPWO2019210237A5/ja
Application granted granted Critical
Publication of JP7162074B2 publication Critical patent/JP7162074B2/ja
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06N3/04—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
    • G06N3/08—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
    • G06N20/00—Machine 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
    • G06N3/044—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
    • G06N3/0464—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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • 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
    • G06N3/0495—Quantised networks; Sparse networks; Compressed 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
    • 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
    • G06N3/06—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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Advance Control (AREA)
  • Feedback Control In General (AREA)
  • Complex Calculations (AREA)
  • Image Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
JP2020558533A 2018-04-27 2019-04-26 機械学習を行うための方法及びシステム Active JP7162074B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201862663955P 2018-04-27 2018-04-27
US62/663,955 2018-04-27
PCT/US2019/029450 WO2019210237A1 (en) 2018-04-27 2019-04-26 Method and system for performing machine learning

Publications (4)

Publication Number Publication Date
JP2021522574A JP2021522574A (ja) 2021-08-30
JP2021522574A5 JP2021522574A5 (https=) 2022-04-07
JPWO2019210237A5 JPWO2019210237A5 (https=) 2022-04-07
JP7162074B2 true JP7162074B2 (ja) 2022-10-27

Family

ID=68291171

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2020558533A Active JP7162074B2 (ja) 2018-04-27 2019-04-26 機械学習を行うための方法及びシステム

Country Status (5)

Country Link
US (1) US11308395B2 (https=)
EP (1) EP3785179A4 (https=)
JP (1) JP7162074B2 (https=)
CN (1) CN111919226B (https=)
WO (1) WO2019210237A1 (https=)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102694572B1 (ko) * 2018-02-20 2024-08-13 삼성전자주식회사 완전 연결 네트워크의 데이터 입력 및 출력을 제어하는 방법 및 장치
TWI767122B (zh) * 2018-05-25 2022-06-11 宏達國際電子股份有限公司 模型建構方法、系統及非揮發性電腦可讀取記錄媒體
US10990850B1 (en) * 2018-12-12 2021-04-27 Amazon Technologies, Inc. Knowledge distillation and automatic model retraining via edge device sample collection
US11537436B2 (en) * 2019-10-02 2022-12-27 Qualcomm Incorporated Method of configuring a memory block allocation of a machine learning network
US20210201110A1 (en) * 2019-12-31 2021-07-01 Alibaba Group Holding Limited Methods and systems for performing inference with a neural network
CN111679959B (zh) * 2020-04-23 2025-04-01 平安科技（深圳）有限公司 计算机性能数据确定方法、装置、计算机设备及存储介质
US20210375441A1 (en) * 2020-05-29 2021-12-02 Regents Of The University Of Minnesota Using clinical notes for icu management
JP7537734B2 (ja) * 2020-08-24 2024-08-21 アシオット株式会社 情報処理装置、及びプログラム
DE102020124174A1 (de) * 2020-09-16 2022-03-17 Elektronische Fahrwerksysteme GmbH Verfahren zur Bereitstellung einer maschinell gelernten Steuerfunktion zur Fahrzeugsteuerung anhand bereitgestellter Fahrzeugsensordaten
WO2022168104A1 (en) * 2021-02-04 2022-08-11 Telefonaktiebolaget Lm Ericsson (Publ) Building an explainable machine learning model
US12125293B2 (en) * 2021-06-17 2024-10-22 Guangzhou Automobile Group Co., Ltd. System, method, and vehicle for recognition of traffic signs
EP4399644A1 (en) * 2021-10-06 2024-07-17 Google LLC Exploring heterogeneous characteristics of layers in asr models for more efficient training
JP7715036B2 (ja) * 2021-12-23 2025-07-30 コニカミノルタ株式会社 ニューラルネットワーク最適化方法、プログラム、および機械学習装置

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015011510A (ja) 2013-06-28 2015-01-19 株式会社デンソーアイティーラボラトリ ニューラルネットワーク最適化方法、ニューラルネットワーク最適化装置及びプログラム
JP2015095215A (ja) 2013-11-14 2015-05-18 株式会社デンソーアイティーラボラトリ 学習装置、学習プログラム、及び学習方法
US20180114110A1 (en) 2016-10-26 2018-04-26 Samsung Electronics Co., Ltd. Method and apparatus to reduce neural network

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2703010B2 (ja) 1988-12-23 1998-01-26 株式会社日立製作所 ニユーラルネツト信号処理プロセツサ
US6760776B1 (en) * 2000-04-10 2004-07-06 International Business Machines Corporation Method and apparatus for processing network frames in a network processor by embedding network control information such as routing and filtering information in each received frame
US8402543B1 (en) * 2011-03-25 2013-03-19 Narus, Inc. Machine learning based botnet detection with dynamic adaptation
US9566710B2 (en) * 2011-06-02 2017-02-14 Brain Corporation Apparatus and methods for operating robotic devices using selective state space training
CN104751228B (zh) * 2013-12-31 2018-04-27 科大讯飞股份有限公司 用于语音识别的深度神经网络的构建方法及系统
CN103914735B (zh) * 2014-04-17 2017-03-29 北京泰乐德信息技术有限公司 一种基于神经网络自学习的故障识别方法及系统
CN104536891B (zh) * 2014-12-26 2017-07-11 小米科技有限责任公司 系统测试方法及装置
CN104679654A (zh) * 2015-02-26 2015-06-03 百度在线网络技术（北京）有限公司 测试应用程序的方法、设备及系统
CN104732231B (zh) 2015-04-13 2019-02-26 广州广电运通金融电子股份有限公司 一种有价票据的识别方法
CN104965790B (zh) * 2015-07-17 2018-04-27 小米科技有限责任公司 基于关键字驱动的软件测试方法及系统
US10885438B2 (en) * 2015-12-28 2021-01-05 Microsoft Technology Licensing, Llc Self-stabilized deep neural network
JP6480644B1 (ja) 2016-03-23 2019-03-13 グーグル エルエルシー マルチチャネル音声認識のための適応的オーディオ強化
CN105844300A (zh) * 2016-03-24 2016-08-10 河南师范大学 一种基于随机森林算法的优化分类方法及装置
CN106445806B (zh) * 2016-08-26 2019-09-17 北京小米移动软件有限公司 软件测试方法及装置
KR102619443B1 (ko) * 2016-09-30 2023-12-28 삼성전자주식회사 손목 온도 리듬 획득 장치 및 방법, 심부 체온 리듬 획득 장치 및 방법과, 웨어러블 디바이스
US20180096249A1 (en) * 2016-10-04 2018-04-05 Electronics And Telecommunications Research Institute Convolutional neural network system using adaptive pruning and weight sharing and operation method thereof
US10366302B2 (en) * 2016-10-10 2019-07-30 Gyrfalcon Technology Inc. Hierarchical category classification scheme using multiple sets of fully-connected networks with a CNN based integrated circuit as feature extractor
CN106775521B (zh) * 2016-11-29 2020-09-08 珠海市魅族科技有限公司 熄屏显示方法和装置
CN107300550A (zh) * 2017-06-21 2017-10-27 南京大学 一种基于bp神经网络模型预测大气重金属浓度的方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2015011510A (ja) 2013-06-28 2015-01-19 株式会社デンソーアイティーラボラトリ ニューラルネットワーク最適化方法、ニューラルネットワーク最適化装置及びプログラム
JP2015095215A (ja) 2013-11-14 2015-05-18 株式会社デンソーアイティーラボラトリ 学習装置、学習プログラム、及び学習方法
US20180114110A1 (en) 2016-10-26 2018-04-26 Samsung Electronics Co., Ltd. Method and apparatus to reduce neural network

Also Published As

Publication number Publication date
CN111919226B (zh) 2025-01-07
WO2019210237A1 (en) 2019-10-31
EP3785179A4 (en) 2021-12-29
US20190332940A1 (en) 2019-10-31
US11308395B2 (en) 2022-04-19
CN111919226A (zh) 2020-11-10
EP3785179A1 (en) 2021-03-03
JP2021522574A (ja) 2021-08-30

Similar Documents

Publication Publication Date Title
JP7162074B2 (ja) 機械学習を行うための方法及びシステム
US11694075B2 (en) Partitioning control dependency edge in computation graph
US11556756B2 (en) Computation graph mapping in heterogeneous computer system
US9754221B1 (en) Processor for implementing reinforcement learning operations
CN109740747B (zh) 运算方法、装置及相关产品
CN112236784B (zh) 修改机器学习模型以改善局部性
JP7108268B2 (ja) 装置間接続を組み込むニューラルネットワークプロセッサ
US10970623B2 (en) System and method for training artificial intelligence systems using a sima based processor
US10949743B2 (en) Method and system for implementing reinforcement learning agent using reinforcement learning processor
US11423284B2 (en) Subgraph tile fusion in a convolutional neural network
US20200301739A1 (en) Maximizing resource utilization of neural network computing system
KR20200088475A (ko) 신경망의 기능적 부분망의 동시 훈련
CN111465943A (zh) 芯片上计算网络
CN116089895A (zh) 一种算子融合方法及装置
KR20210083624A (ko) 신경망의 데이터 입력 및 출력을 제어하는 제어 방법 및 장치
CN113496248A (zh) 训练计算机实施的模型的方法和设备
KR102730318B1 (ko) 모델 경량화 및 전이학습의 융합에 기반한 전이학습 모델 획득 방법 및 시스템
US11113140B2 (en) Detecting error in executing computation graph on heterogeneous computing devices
CN117312839B (zh) 模型训练方法、装置、系统及相关设备
US20210248073A1 (en) System and method for memory management
US12400137B1 (en) Bidirectional network on a data-flow centric processor
KR102490538B1 (ko) 강화 학습 기반의 프로그램 최적화 방법
CN119398129A (zh) 目标策略模型的训练方法、指令执行方法、装置及介质
WO2020113459A1 (en) Intermediate representation transformation by slice operation hoist

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220330

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20220330

A871 Explanation of circumstances concerning accelerated examination

Free format text: JAPANESE INTERMEDIATE CODE: A871

Effective date: 20220330

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20220428

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220719

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: 20220927

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20221017

R150 Certificate of patent or registration of utility model

Ref document number: 7162074

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150

S111 Request for change of ownership or part of ownership

Free format text: JAPANESE INTERMEDIATE CODE: R313113

R350 Written notification of registration of transfer

Free format text: JAPANESE INTERMEDIATE CODE: R350

R250 Receipt of annual fees

Free format text: JAPANESE INTERMEDIATE CODE: R250