KR20230050340A - 테이블 형식의 컨볼루션 및 가속 - Google Patents

테이블 형식의 컨볼루션 및 가속 Download PDF

Info

Publication number
KR20230050340A
KR20230050340A KR1020237005045A KR20237005045A KR20230050340A KR 20230050340 A KR20230050340 A KR 20230050340A KR 1020237005045 A KR1020237005045 A KR 1020237005045A KR 20237005045 A KR20237005045 A KR 20237005045A KR 20230050340 A KR20230050340 A KR 20230050340A
Authority
KR
South Korea
Prior art keywords
input data
convolution
output
pointer
tabular
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
KR1020237005045A
Other languages
English (en)
Korean (ko)
Inventor
제이미 멘제이 린
시종 스티브 한
파티 무라트 포리클리
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 KR20230050340A publication Critical patent/KR20230050340A/ko
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G06F17/153—Multidimensional correlation or convolution
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/25—Integrating or interfacing systems involving database management systems
    • G06F16/258—Data format conversion from or to a database
    • 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
    • G06N3/04—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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/40—Analysis of texture
    • G06T7/41—Analysis of texture based on statistical description of texture
    • G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
    • G06V30/195—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references using a resistor matrix
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30204—Marker
    • G06T2207/30208—Marker matrix

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Multimedia (AREA)
  • Algebra (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Complex Calculations (AREA)
KR1020237005045A 2020-08-21 2021-08-20 테이블 형식의 컨볼루션 및 가속 Pending KR20230050340A (ko)

Applications Claiming Priority (5)

Application Number Priority Date Filing Date Title
US202063068891P 2020-08-21 2020-08-21
US63/068,891 2020-08-21
US17/407,046 US12080086B2 (en) 2020-08-21 2021-08-19 Sparse-aware convolution and techniques for acceleration thereof
US17/407,046 2021-08-19
PCT/US2021/046977 WO2022040575A1 (en) 2020-08-21 2021-08-20 Tabular convolution and acceleration

Publications (1)

Publication Number Publication Date
KR20230050340A true KR20230050340A (ko) 2023-04-14

Family

ID=80269644

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020237005045A Pending KR20230050340A (ko) 2020-08-21 2021-08-20 테이블 형식의 컨볼루션 및 가속

Country Status (7)

Country Link
US (1) US12080086B2 (https=)
EP (1) EP4200722A1 (https=)
JP (1) JP7710507B2 (https=)
KR (1) KR20230050340A (https=)
CN (1) CN116075821A (https=)
BR (1) BR112023002375A2 (https=)
WO (1) WO2022040575A1 (https=)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12080086B2 (en) * 2020-08-21 2024-09-03 Qualcomm Incorporated Sparse-aware convolution and techniques for acceleration thereof
US20230086378A1 (en) * 2021-09-22 2023-03-23 Qualcomm Incorporated Shaped convolution kernels
CN114580613B (zh) * 2022-03-01 2025-03-25 珠海亿智电子科技有限公司 一种数据处理方法、装置、终端及存储介质
US11868329B2 (en) * 2022-05-20 2024-01-09 International Business Machines Corporation Multidimensional cube multivariate regression
CN115639935B (zh) * 2022-12-14 2023-03-14 亿海蓝（北京）数据技术股份公司 表格操作方法、装置和可读存储介质
US20240320299A1 (en) * 2023-03-02 2024-09-26 Imagination Technologies Limited Methods and systems for performing a standard deconvolution on a gpu
CN116935233B (zh) * 2023-09-15 2023-12-12 瀚博半导体(上海)有限公司 用于激光雷达的目标检测方法和装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB0400974D0 (en) * 2004-01-16 2004-02-18 Solexa Ltd Multiple inexact matching
US9104271B1 (en) * 2011-06-03 2015-08-11 Richard Adams Gloved human-machine interface
KR102499396B1 (ko) 2017-03-03 2023-02-13 삼성전자 주식회사 뉴럴 네트워크 장치 및 뉴럴 네트워크 장치의 동작 방법
JP7034837B2 (ja) 2018-06-01 2022-03-14 株式会社デンソーアイティーラボラトリ ３次元畳込み演算装置、ビジュアルオドメトリシステム、及び３次元畳込みプログラム
US10846524B2 (en) * 2018-11-14 2020-11-24 Adobe Inc. Table layout determination using a machine learning system
US10997729B2 (en) * 2018-11-30 2021-05-04 Baidu Usa Llc Real time object behavior prediction
US12080086B2 (en) * 2020-08-21 2024-09-03 Qualcomm Incorporated Sparse-aware convolution and techniques for acceleration thereof

Also Published As

Publication number Publication date
US12080086B2 (en) 2024-09-03
JP7710507B2 (ja) 2025-07-18
US20220058450A1 (en) 2022-02-24
WO2022040575A1 (en) 2022-02-24
JP2023541350A (ja) 2023-10-02
CN116075821A (zh) 2023-05-05
BR112023002375A2 (pt) 2023-03-21
EP4200722A1 (en) 2023-06-28

Similar Documents

Publication Publication Date Title
US12080086B2 (en) Sparse-aware convolution and techniques for acceleration thereof
US20190347537A1 (en) Efficient Convolutional Neural Networks and Techniques to Reduce Associated Computational Costs
CN114651260A (zh) 具有动态权重选择的相位选择性卷积
CN111008631B (zh) 图像的关联方法及装置、存储介质和电子装置
WO2017116924A1 (en) Neural network training performance optimization framework
Tridgell et al. Unrolling ternary neural networks
CN111709415B (zh) 目标检测方法、装置、计算机设备和存储介质
CN109117940B (zh) 基于卷积神经网络的目标检测方法、装置、终端及存储介质
EP4270247A1 (en) Neural network model training method and apparatus, and data processing method and apparatus
KR102869716B1 (ko) 기계 학습 가속을 위한 전력 감소
CN112232477B (zh) 图像数据处理方法、装置、设备及介质
CN116888605B (zh) 神经网络模型的运算方法、训练方法及装置
US20240028665A1 (en) Apparatus and method for computing a matrix vector product of a certain matrix and a vector
WO2023165290A1 (zh) 数据处理方法及装置、电子设备和存储介质
CN115952391A (zh) 数据处理方法及装置、电子设备与存储介质
WO2023115814A1 (zh) Fpga硬件架构及其数据处理方法、存储介质
WO2021247764A1 (en) Structured convolutions and associated acceleration
WO2024222115A1 (zh) 神经网络的剪枝方法、数据处理方法及装置
US20220309344A1 (en) Broadcasted residual learning
CN114365155B (zh) 具有快速逐点卷积的高效推断
GB2618399A (en) Implementing a scatter function on a neural network accelerator
GB2618398A (en) Implementing a scatter function on a neural network accelerator
EP4361891A1 (en) Implementing a scatter function on a neural network accelerator
WO2023053222A1 (ja) データ変換装置、データ変換方法、及びプログラムが格納された非一時的なコンピュータ可読媒体
WO2024238020A1 (en) Outlier attenuation in transformer neural networks

Legal Events

Date Code Title Description
PA0105 International application

Patent event date: 20230213

Patent event code: PA01051R01D

Comment text: International Patent Application

PG1501 Laying open of application
A201 Request for examination
PA0201 Request for examination

Patent event code: PA02012R01D

Patent event date: 20240805

Comment text: Request for Examination of Application