KR102570706B1 - 분류를 위한 강제된 희소성 - Google Patents

분류를 위한 강제된 희소성 Download PDF

Info

Publication number
KR102570706B1
KR102570706B1 KR1020187009144A KR20187009144A KR102570706B1 KR 102570706 B1 KR102570706 B1 KR 102570706B1 KR 1020187009144 A KR1020187009144 A KR 1020187009144A KR 20187009144 A KR20187009144 A KR 20187009144A KR 102570706 B1 KR102570706 B1 KR 102570706B1
Authority
KR
South Korea
Prior art keywords
elements
feature vector
memory
retained
sparse
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
KR1020187009144A
Other languages
English (en)
Korean (ko)
Other versions
KR20180048930A (ko
Inventor
솜뎁 마줌다르
레건 블라이스 토월
Original Assignee
퀄컴 인코포레이티드
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 퀄컴 인코포레이티드 filed Critical 퀄컴 인코포레이티드
Publication of KR20180048930A publication Critical patent/KR20180048930A/ko
Application granted granted Critical
Publication of KR102570706B1 publication Critical patent/KR102570706B1/ko
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
    • G06N3/08—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
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace 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
    • G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
    • G06F18/2136—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on sparsity criteria, e.g. with an overcomplete basis
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • 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
    • G06N3/0464—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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
    • G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
    • G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/7715—Feature extraction, e.g. by transforming the feature space, e.g. multi-dimensional scaling [MDS]; Mappings, e.g. subspace methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06Y10/50—

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Medical Informatics (AREA)
  • Databases & Information Systems (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Image Analysis (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
KR1020187009144A 2015-09-02 2016-08-04 분류를 위한 강제된 희소성 Active KR102570706B1 (ko)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US201562213591P 2015-09-02 2015-09-02
US62/213,591 2015-09-02
US15/077,873 2016-03-22
US15/077,873 US11423323B2 (en) 2015-09-02 2016-03-22 Generating a sparse feature vector for classification
PCT/US2016/045636 WO2017039946A1 (en) 2015-09-02 2016-08-04 Enforced sparsity for classification

Publications (2)

Publication Number Publication Date
KR20180048930A KR20180048930A (ko) 2018-05-10
KR102570706B1 true KR102570706B1 (ko) 2023-08-24

Family

ID=58104178

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020187009144A Active KR102570706B1 (ko) 2015-09-02 2016-08-04 분류를 위한 강제된 희소성

Country Status (7)

Country Link
US (1) US11423323B2 (cg-RX-API-DMAC7.html)
EP (1) EP3345133A1 (cg-RX-API-DMAC7.html)
JP (1) JP7037478B2 (cg-RX-API-DMAC7.html)
KR (1) KR102570706B1 (cg-RX-API-DMAC7.html)
CN (1) CN107924486A (cg-RX-API-DMAC7.html)
CA (1) CA2993011C (cg-RX-API-DMAC7.html)
WO (1) WO2017039946A1 (cg-RX-API-DMAC7.html)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170178346A1 (en) * 2015-12-16 2017-06-22 High School Cube, Llc Neural network architecture for analyzing video data
AU2016277542A1 (en) * 2016-12-19 2018-07-05 Canon Kabushiki Kaisha Method for training an artificial neural network
US10490182B1 (en) * 2016-12-29 2019-11-26 Amazon Technologies, Inc. Initializing and learning rate adjustment for rectifier linear unit based artificial neural networks
CN109284823B (zh) * 2017-04-20 2020-08-04 上海寒武纪信息科技有限公司 一种运算装置及相关产品
WO2018214913A1 (zh) * 2017-05-23 2018-11-29 上海寒武纪信息科技有限公司 处理方法及加速装置
CN107316065B (zh) * 2017-06-26 2021-03-02 刘艳 基于分部式子空间模型的稀疏特征提取和分类方法
CN107609599B (zh) * 2017-09-27 2020-09-08 北京小米移动软件有限公司 特征识别方法及装置
US10055685B1 (en) 2017-10-16 2018-08-21 Apprente, Inc. Machine learning architecture for lifelong learning
US10325223B1 (en) 2018-02-06 2019-06-18 Apprente, Inc. Recurrent machine learning system for lifelong learning
US10162794B1 (en) * 2018-03-07 2018-12-25 Apprente, Inc. Hierarchical machine learning system for lifelong learning
CN109905271B (zh) * 2018-05-18 2021-01-12 华为技术有限公司 一种预测方法、训练方法、装置及计算机存储介质
US20210326662A1 (en) * 2018-07-19 2021-10-21 Nokia Technologies Oy Environment modeling and abstraction of network states for cognitive functions
EP3888390A1 (en) * 2018-11-28 2021-10-06 Nokia Solutions and Networks Oy A method and an apparatus for fault prediction in network management
JP7131356B2 (ja) * 2018-12-11 2022-09-06 富士通株式会社 最適化装置、最適化プログラムおよび最適化方法
KR20200125531A (ko) * 2019-04-25 2020-11-04 주식회사 마이셀럽스 언어 단위와 이용 내역 간의 연관도를 이용한 항목 추천 관리 방법
CN110321866B (zh) * 2019-07-09 2023-03-24 西北工业大学 基于深度特征稀疏化算法的遥感图像场景分类方法
US12400137B1 (en) * 2019-09-30 2025-08-26 Amazon Technologies, Inc. Bidirectional network on a data-flow centric processor
US12236341B2 (en) * 2020-09-30 2025-02-25 Moffett International Co., Limited Bank-balanced-sparse activation feature maps for neural network models
KR20230043318A (ko) * 2021-09-24 2023-03-31 삼성전자주식회사 영상 내 객체를 분류하는 객체 분류 방법 및 장치
WO2024072924A2 (en) * 2022-09-28 2024-04-04 Google Llc Scalable feature selection via sparse learnable masks
US20250217640A1 (en) * 2023-02-16 2025-07-03 Micron Technology, Inc. Training Deep Learning Models based on Characteristics of Accelerators for Improved Energy Efficiency in Accelerating Computations of the Models

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030139929A1 (en) 2002-01-24 2003-07-24 Liang He Data transmission system and method for DSR application over GPRS
US20150139559A1 (en) * 2012-09-14 2015-05-21 Google Inc. System and method for shape clustering using hierarchical character classifiers

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6633817B1 (en) * 1999-12-29 2003-10-14 Incyte Genomics, Inc. Sequence database search with sequence search trees
US7016529B2 (en) 2002-03-15 2006-03-21 Microsoft Corporation System and method facilitating pattern recognition
US20090274376A1 (en) * 2008-05-05 2009-11-05 Yahoo! Inc. Method for efficiently building compact models for large multi-class text classification
US8374442B2 (en) 2008-11-19 2013-02-12 Nec Laboratories America, Inc. Linear spatial pyramid matching using sparse coding
US20100161527A1 (en) * 2008-12-23 2010-06-24 Yahoo! Inc. Efficiently building compact models for large taxonomy text classification
CN102073880A (zh) 2011-01-13 2011-05-25 西安电子科技大学 利用稀疏表示进行人脸识别的集成方法
CN103106535B (zh) 2013-02-21 2015-05-13 电子科技大学 一种基于神经网络解决协同过滤推荐数据稀疏性的方法
US9147154B2 (en) 2013-03-13 2015-09-29 Google Inc. Classifying resources using a deep network
US10095917B2 (en) 2013-11-04 2018-10-09 Facebook, Inc. Systems and methods for facial representation

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030139929A1 (en) 2002-01-24 2003-07-24 Liang He Data transmission system and method for DSR application over GPRS
US20150139559A1 (en) * 2012-09-14 2015-05-21 Google Inc. System and method for shape clustering using hierarchical character classifiers

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Adam Coates et. al., Proceedings of the 28th International Conference on International Conference on Machine LearningJune, Pages 921-928, 2011*

Also Published As

Publication number Publication date
CA2993011A1 (en) 2017-03-09
CN107924486A (zh) 2018-04-17
JP7037478B2 (ja) 2022-03-16
JP2018527677A (ja) 2018-09-20
CA2993011C (en) 2023-09-19
KR20180048930A (ko) 2018-05-10
EP3345133A1 (en) 2018-07-11
BR112018004219A2 (pt) 2018-09-25
US11423323B2 (en) 2022-08-23
WO2017039946A1 (en) 2017-03-09
US20170061328A1 (en) 2017-03-02

Similar Documents

Publication Publication Date Title
US11423323B2 (en) Generating a sparse feature vector for classification
KR102595399B1 (ko) 미지의 클래스들의 검출 및 미지의 클래스들에 대한 분류기들의 초기화
KR102806514B1 (ko) 뉴럴 네트워크들에서의 러닝을 트랜스퍼하기 위한 장치들 및 방법들
KR102826736B1 (ko) 트레이닝된 머신 학습 모델의 성능을 개선시키는 방법
CN107209873B (zh) 用于深度卷积网络的超参数选择
US11334789B2 (en) Feature selection for retraining classifiers
US20170091619A1 (en) Selective backpropagation
US20160328644A1 (en) Adaptive selection of artificial neural networks
EP3295382A1 (en) Bit width selection for fixed point neural networks
CN107430703A (zh) 对细调特征的顺序图像采样和存储
KR20260018839A (ko) 그래프 뉴럴 네트워크들을 사용한 딥 뉴럴 네트워크 컴파일을 위한 프리프로세싱
WO2021158830A1 (en) Rounding mechanisms for post-training quantization
US20260093771A1 (en) Efficient one-dimensional (1d) convolution support on two-dimensional (2d) convolution engines
KR20260020927A (ko) 그래프 뉴럴 네트워크들을 사용한 딥 뉴럴 네트워크 컴파일을 위한 프리프로세싱
WO2023004670A1 (en) Channel-guided nested loop transformation and scalar replacement

Legal Events

Date Code Title Description
PA0105 International application

St.27 status event code: A-0-1-A10-A15-nap-PA0105

PG1501 Laying open of application

St.27 status event code: A-1-1-Q10-Q12-nap-PG1501

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

A201 Request for examination
PA0201 Request for examination

St.27 status event code: A-1-2-D10-D11-exm-PA0201

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

D13-X000 Search requested

St.27 status event code: A-1-2-D10-D13-srh-X000

D14-X000 Search report completed

St.27 status event code: A-1-2-D10-D14-srh-X000

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

E902 Notification of reason for refusal
PE0902 Notice of grounds for rejection

St.27 status event code: A-1-2-D10-D21-exm-PE0902

E13-X000 Pre-grant limitation requested

St.27 status event code: A-2-3-E10-E13-lim-X000

P11-X000 Amendment of application requested

St.27 status event code: A-2-2-P10-P11-nap-X000

P13-X000 Application amended

St.27 status event code: A-2-2-P10-P13-nap-X000

P22-X000 Classification modified

St.27 status event code: A-2-2-P10-P22-nap-X000

E701 Decision to grant or registration of patent right
PE0701 Decision of registration

St.27 status event code: A-1-2-D10-D22-exm-PE0701

GRNT Written decision to grant
PR0701 Registration of establishment

St.27 status event code: A-2-4-F10-F11-exm-PR0701

PR1002 Payment of registration fee

St.27 status event code: A-2-2-U10-U12-oth-PR1002

Fee payment year number: 1

PG1601 Publication of registration

St.27 status event code: A-4-4-Q10-Q13-nap-PG1601

P22-X000 Classification modified

St.27 status event code: A-4-4-P10-P22-nap-X000

PR1001 Payment of annual fee

St.27 status event code: A-4-4-U10-U11-oth-PR1001

Fee payment year number: 4

U11 Full renewal or maintenance fee paid

Free format text: ST27 STATUS EVENT CODE: A-4-4-U10-U11-OTH-PR1001 (AS PROVIDED BY THE NATIONAL OFFICE)

Year of fee payment: 4