CN106462797A - 共同特征上的定制分类器 - Google Patents

共同特征上的定制分类器 Download PDF

Info

Publication number
CN106462797A
CN106462797A CN201580024851.2A CN201580024851A CN106462797A CN 106462797 A CN106462797 A CN 106462797A CN 201580024851 A CN201580024851 A CN 201580024851A CN 106462797 A CN106462797 A CN 106462797A
Authority
CN
China
Prior art keywords
model
user
grader
distributed
classifier
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
CN201580024851.2A
Other languages
English (en)
Chinese (zh)
Inventor
C·M·维任斯基
D·J·朱利安
A·莎拉
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.)
Qualcomm Inc
Original Assignee
Qualcomm Inc
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 Qualcomm Inc filed Critical Qualcomm Inc
Publication of CN106462797A publication Critical patent/CN106462797A/zh
Pending legal-status Critical Current

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
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • 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
    • 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
    • G06N3/045—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
    • G06N3/045—Combinations of networks
    • G06N3/0455—Auto-encoder networks; Encoder-decoder 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
    • G06N3/04—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
    • 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
    • G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-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
    • G06N3/09—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
    • G06N3/091—Active 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
    • G06N3/096—Transfer 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
    • 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

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)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
CN201580024851.2A 2014-05-12 2015-04-20 共同特征上的定制分类器 Pending CN106462797A (zh)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201461992168P 2014-05-12 2014-05-12
US61/992,168 2014-05-12
US14/483,054 2014-09-10
US14/483,054 US20150324688A1 (en) 2014-05-12 2014-09-10 Customized classifier over common features
PCT/US2015/026621 WO2015175156A1 (en) 2014-05-12 2015-04-20 Customized classifier over common features

Publications (1)

Publication Number Publication Date
CN106462797A true CN106462797A (zh) 2017-02-22

Family

ID=54368122

Family Applications (2)

Application Number Title Priority Date Filing Date
CN201580024851.2A Pending CN106462797A (zh) 2014-05-12 2015-04-20 共同特征上的定制分类器
CN201580025183.5A Active CN106575377B (zh) 2014-05-12 2015-04-20 共同特征上的分类器更新

Family Applications After (1)

Application Number Title Priority Date Filing Date
CN201580025183.5A Active CN106575377B (zh) 2014-05-12 2015-04-20 共同特征上的分类器更新

Country Status (6)

Country Link
US (2) US20150324688A1 (enExample)
EP (2) EP3143561A1 (enExample)
JP (2) JP2017520825A (enExample)
KR (2) KR20170008748A (enExample)
CN (2) CN106462797A (enExample)
WO (2) WO2015175156A1 (enExample)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111729310A (zh) * 2020-06-24 2020-10-02 网易（杭州）网络有限公司 游戏道具的整理方法、装置和电子设备
CN112534447A (zh) * 2018-08-03 2021-03-19 西门子医疗保健诊断公司 训练用于控制工程系统的机器学习例程的方法和设备

Families Citing this family (60)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9990587B2 (en) * 2015-01-22 2018-06-05 Preferred Networks, Inc. Machine learning heterogeneous edge device, method, and system
US10387794B2 (en) * 2015-01-22 2019-08-20 Preferred Networks, Inc. Machine learning with model filtering and model mixing for edge devices in a heterogeneous environment
US20160379139A1 (en) * 2015-06-29 2016-12-29 Secure Islands Technologies Ltd. Adaptive classification of data items
US10937168B2 (en) 2015-11-02 2021-03-02 Cognex Corporation System and method for finding and classifying lines in an image with a vision system
DE102016120775B4 (de) 2015-11-02 2025-02-20 Cognex Corporation System und Verfahren zum Erkennen von Linien in einem Bild mit einem Sichtsystem
US11210595B2 (en) * 2015-11-30 2021-12-28 Allegro Artificial Intelligence Ltd System and method for selective use of examples
US10454877B2 (en) 2016-04-29 2019-10-22 Cisco Technology, Inc. Interoperability between data plane learning endpoints and control plane learning endpoints in overlay networks
US9984314B2 (en) * 2016-05-06 2018-05-29 Microsoft Technology Licensing, Llc Dynamic classifier selection based on class skew
US10091070B2 (en) 2016-06-01 2018-10-02 Cisco Technology, Inc. System and method of using a machine learning algorithm to meet SLA requirements
CN109478311A (zh) 2016-07-30 2019-03-15 华为技术有限公司 一种图像识别方法及终端
US20180089581A1 (en) * 2016-09-27 2018-03-29 Futurewei Technologies, Inc. Apparatus and method for dataset model fitting using a classifying engine
EP3520038A4 (en) 2016-09-28 2020-06-03 D5A1 Llc LEARNING TRAINER FOR MACHINE LEARNING SYSTEM
US20180129900A1 (en) * 2016-11-04 2018-05-10 Siemens Healthcare Gmbh Anonymous and Secure Classification Using a Deep Learning Network
US20180144244A1 (en) * 2016-11-23 2018-05-24 Vital Images, Inc. Distributed clinical workflow training of deep learning neural networks
US10699184B2 (en) * 2016-12-29 2020-06-30 Facebook, Inc. Updating predictions for a deep-learning model
WO2018175098A1 (en) * 2017-03-24 2018-09-27 D5Ai Llc Learning coach for machine learning system
US10963813B2 (en) 2017-04-28 2021-03-30 Cisco Technology, Inc. Data sovereignty compliant machine learning
CN108959304B (zh) * 2017-05-22 2022-03-25 阿里巴巴集团控股有限公司 一种标签预测方法及装置
US10467324B2 (en) 2017-05-24 2019-11-05 Microsoft Technology Licensing, Llc Data packing techniques for hard-wired multiplier circuits
US11295210B2 (en) 2017-06-05 2022-04-05 D5Ai Llc Asynchronous agents with learning coaches and structurally modifying deep neural networks without performance degradation
JP6869817B2 (ja) * 2017-06-07 2021-05-12 Kddi株式会社 管理装置、管理方法、及びプログラム
US10346724B2 (en) * 2017-06-22 2019-07-09 Waymo Llc Rare instance classifiers
US10477148B2 (en) 2017-06-23 2019-11-12 Cisco Technology, Inc. Speaker anticipation
US10608901B2 (en) 2017-07-12 2020-03-31 Cisco Technology, Inc. System and method for applying machine learning algorithms to compute health scores for workload scheduling
US10091348B1 (en) 2017-07-25 2018-10-02 Cisco Technology, Inc. Predictive model for voice/video over IP calls
KR102610820B1 (ko) * 2017-09-27 2023-12-06 삼성전자주식회사 뉴럴 네트워크 시스템 및 뉴럴 네트워크 시스템의 동작방법
EP3718056A1 (en) 2017-12-01 2020-10-07 Telefonaktiebolaget LM Ericsson (publ) Selecting learning model
EP3518156A1 (en) * 2018-01-29 2019-07-31 Siemens Aktiengesellschaft A method for collaborative machine learning of analytical models
US11321612B2 (en) 2018-01-30 2022-05-03 D5Ai Llc Self-organizing partially ordered networks and soft-tying learned parameters, such as connection weights
CN108829441B (zh) * 2018-05-14 2022-10-18 中山大学 一种分布式深度学习的参数更新优化系统
US10867067B2 (en) 2018-06-07 2020-12-15 Cisco Technology, Inc. Hybrid cognitive system for AI/ML data privacy
US10446170B1 (en) 2018-06-19 2019-10-15 Cisco Technology, Inc. Noise mitigation using machine learning
US12169792B2 (en) 2018-06-22 2024-12-17 International Business Machines Corporation Adaptive multi-agent cooperative computation and inference
EP3826893A4 (en) * 2018-07-23 2022-04-20 HRL Laboratories, LLC A method of real time vehicle recognition with neuromorphic computing network for autonomous driving
CN109040489B (zh) * 2018-08-02 2021-01-26 中国联合网络通信集团有限公司 电信客服的分配方法和装置
JP6981554B2 (ja) * 2018-09-14 2021-12-15 日本電気株式会社 識別システム、パラメータ値更新方法およびプログラム
KR102095132B1 (ko) * 2018-11-29 2020-03-30 한국과학기술원 음성 검출을 위한 잡음제거 변분 오토인코더 기반의 통합 훈련 방법 및 장치
CN109753580A (zh) * 2018-12-21 2019-05-14 Oppo广东移动通信有限公司 一种图像分类方法、装置、存储介质及电子设备
US11068694B2 (en) * 2019-01-23 2021-07-20 Molecular Devices, Llc Image analysis system and method of using the image analysis system
US10832407B2 (en) * 2019-03-06 2020-11-10 International Business Machines Corporation Training a neural network adapter
JP7171477B2 (ja) * 2019-03-14 2022-11-15 ヤフー株式会社 情報処理装置、情報処理方法および情報処理プログラム
US11562248B2 (en) * 2019-04-29 2023-01-24 Advanced Micro Devices, Inc. Data sparsity monitoring during neural network training
US20200364503A1 (en) * 2019-05-15 2020-11-19 International Business Machines Corporation Accurate ensemble by mutating neural network parameters
US11308284B2 (en) 2019-10-18 2022-04-19 Facebook Technologies, Llc. Smart cameras enabled by assistant systems
GB2588614B (en) * 2019-10-29 2023-01-11 Samsung Electronics Co Ltd Method and system for customising a machine learning model
EP3997625A4 (en) 2019-10-29 2022-11-09 Samsung Electronics Co., Ltd. ELECTRONIC DEVICE AND CONTROL METHOD THEREOF
US11681922B2 (en) * 2019-11-26 2023-06-20 Numenta, Inc. Performing inference and training using sparse neural network
US11696119B2 (en) * 2019-12-16 2023-07-04 Qualcomm Incorporated Neural network configuration for wireless communication system assistance
CN111242167B (zh) * 2019-12-30 2023-11-14 深圳奇迹智慧网络有限公司 分布式图像标注方法、装置、计算机设备和存储介质
US20220067486A1 (en) * 2020-09-02 2022-03-03 Sap Se Collaborative learning of question generation and question answering
CN116324820A (zh) * 2020-09-28 2023-06-23 高通股份有限公司 诱发稀疏性的联合机器学习
US12386621B2 (en) * 2020-12-14 2025-08-12 Cognitive Science & Solutions, Inc. AI synaptic coprocessor
US11599360B2 (en) * 2020-12-14 2023-03-07 Cognitive Science & Solutions, Inc. AI synaptic coprocessor
US20220414316A1 (en) * 2021-06-23 2022-12-29 International Business Machines Corporation Automated language assessment for web applications using natural language processing
KR102620697B1 (ko) * 2021-07-12 2024-01-02 주식회사 카카오뱅크 딥러닝 기반의 자연어 처리를 통한 메시지 내 이체 정보 판단 방법 및 장치
KR102405726B1 (ko) * 2021-09-08 2022-06-07 에이엠스퀘어 주식회사 클라우드 데이터 전송 정보량의 최적화를 위한 뉴런 모델 기반 제어 장치 및 제어 방법
US20230376736A1 (en) * 2022-05-23 2023-11-23 International Business Machines Corporation Neuron circuits for spiking neural networks
CN114861900B (zh) * 2022-05-27 2024-09-13 清华大学 用于忆阻器阵列的权重更新方法和处理单元
JPWO2024116402A1 (enExample) * 2022-12-02 2024-06-06
WO2025172980A1 (en) * 2024-04-04 2025-08-21 Lenovo (Singapore) Pte. Ltd. Obtaining parameters for a learning model

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100177956A1 (en) * 2009-01-13 2010-07-15 Matthew Cooper Systems and methods for scalable media categorization
US20110022615A1 (en) * 2009-07-21 2011-01-27 National Taiwan University Digital data processing method for personalized information retrieval and computer readable storage medium and information retrieval system thereof

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05324598A (ja) * 1992-05-19 1993-12-07 Fujitsu Ltd ニューラル・ネットワーク学習装置における学習方式
US7349917B2 (en) * 2002-10-01 2008-03-25 Hewlett-Packard Development Company, L.P. Hierarchical categorization method and system with automatic local selection of classifiers
WO2009129008A1 (en) * 2008-04-17 2009-10-22 University Of Utah Research Foundation Multi-channel acoustic echo cancellation system and method
CN101877837B (zh) * 2009-04-30 2013-11-06 华为技术有限公司 一种短信过滤的方法和装置
KR101472452B1 (ko) * 2010-11-17 2014-12-17 한국전자통신연구원 멀티미디어 데이터 검색 방법, 장치 및 패턴인식 방법
US8719192B2 (en) * 2011-04-06 2014-05-06 Microsoft Corporation Transfer of learning for query classification
JP5834468B2 (ja) * 2011-04-27 2015-12-24 ソニー株式会社 情報処理装置、情報処理方法、及び、プログラム
JP5565869B2 (ja) * 2011-08-01 2014-08-06 株式会社ユニバーサルエンターテインメント 識別装置及び識別プログラム
US20130304677A1 (en) * 2012-05-14 2013-11-14 Qualcomm Incorporated Architecture for Client-Cloud Behavior Analyzer
CN103679185B (zh) * 2012-08-31 2017-06-16 富士通株式会社 卷积神经网络分类器系统、其训练方法、分类方法和用途
US9292798B2 (en) * 2012-12-21 2016-03-22 International Business Machines Corporation Iterative active feature extraction
US11669748B2 (en) * 2013-05-14 2023-06-06 David Lebow Collaborative sensemaking system and method

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100177956A1 (en) * 2009-01-13 2010-07-15 Matthew Cooper Systems and methods for scalable media categorization
US20110022615A1 (en) * 2009-07-21 2011-01-27 National Taiwan University Digital data processing method for personalized information retrieval and computer readable storage medium and information retrieval system thereof

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112534447A (zh) * 2018-08-03 2021-03-19 西门子医疗保健诊断公司 训练用于控制工程系统的机器学习例程的方法和设备
CN112534447B (zh) * 2018-08-03 2024-05-24 西门子医疗保健诊断公司 训练用于控制工程系统的机器学习例程的方法和设备
CN111729310A (zh) * 2020-06-24 2020-10-02 网易（杭州）网络有限公司 游戏道具的整理方法、装置和电子设备
CN111729310B (zh) * 2020-06-24 2024-02-09 网易（杭州）网络有限公司 游戏道具的整理方法、装置和电子设备

Also Published As

Publication number Publication date
EP3143561A1 (en) 2017-03-22
CN106575377A (zh) 2017-04-19
US20150324688A1 (en) 2015-11-12
JP2017520824A (ja) 2017-07-27
EP3143560C0 (en) 2024-03-20
JP2017520825A (ja) 2017-07-27
KR20170008748A (ko) 2017-01-24
US20150324689A1 (en) 2015-11-12
CN106575377B (zh) 2020-05-08
WO2015175156A1 (en) 2015-11-19
KR20170008747A (ko) 2017-01-24
EP3143560B1 (en) 2024-03-20
WO2015175154A1 (en) 2015-11-19
EP3143560A1 (en) 2017-03-22

Similar Documents

Publication Publication Date Title
EP3143563B1 (en) Distributed model learning
CN106575377B (zh) 共同特征上的分类器更新
Kadhim et al. Artificial Neural Network Hyperparameters Optimization: A Survey.
CN106663221B (zh) 由知识图谱偏置的数据分类
CN106104577B (zh) 照片管理
US11468337B2 (en) System and methods for facilitating pattern recognition
US20150269481A1 (en) Differential encoding in neural networks
CN105874477A (zh) 配置稀疏神经网络
Skatchkovsky et al. Bayesian continual learning via spiking neural networks
Perwej et al. Forecasting of Indian Rupee (INR)/US Dollar (USD) currency exchange rate using artificial neural network
Gurusamy et al. DGSLSTM: deep gated stacked long short-term memory neural network for traffic flow forecasting of transportation networks on big data environment
Gavrilov et al. Convolutional neural networks: Estimating relations in the ising model on overfitting
CN113779396B (zh) 题目推荐方法和装置、电子设备、存储介质
Xiang et al. Semi-parametric training of autoencoders with Gaussian kernel smoothed topology learning neural networks
CN120974002A (zh) 基于脉冲神经网络的边缘设备多模态信息序列推荐方法
Besedin Continual forgetting-free deep learning from high-dimensional data streams
Yalavarthi A hybrid machine learning technique for complex non-stationary classification problems
Mishra et al. A Neuro-Inspired Approach for Continual Multi-Label Learning with Evolving Spiking Networks
HK1232650A1 (en) Knowledge-graph biased classification for data

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20170222