MX2019004654A - Calculo rapido de una red neuronal convolucional. - Google Patents

Calculo rapido de una red neuronal convolucional.

Info

Publication number
MX2019004654A
MX2019004654A MX2019004654A MX2019004654A MX2019004654A MX 2019004654 A MX2019004654 A MX 2019004654A MX 2019004654 A MX2019004654 A MX 2019004654A MX 2019004654 A MX2019004654 A MX 2019004654A MX 2019004654 A MX2019004654 A MX 2019004654A
Authority
MX
Mexico
Prior art keywords
neural network
convolutional
convolutional neural
convolutional layers
trained
Prior art date
Application number
MX2019004654A
Other languages
English (en)
Inventor
Lin Wang
Haitao Zhang
Yongchao Liu
Qiyin Huang
Guozhen Pan
Jianguo Xu
Sizhong Li
Original Assignee
Advanced New Technologies Co Ltd
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 Advanced New Technologies Co Ltd filed Critical Advanced New Technologies Co Ltd
Publication of MX2019004654A publication Critical patent/MX2019004654A/es

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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
    • G06V30/191—Design or setup of recognition systems or techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G06V30/19173—Classification techniques

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Neurology (AREA)
  • Medical Informatics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Databases & Information Systems (AREA)
  • Human Computer Interaction (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Image Analysis (AREA)

Abstract

Un método implementado por computadora incluye obtener una red neuronal convolucional entrenada que comprende una o más capas convolucionales, cada una de la una o más capas convolucionales comprenden una pluralidad de filtros con parámetros de filtro conocidos; precalcular un factor reutilizable para cada una de la una o más capas convolucionales con base en los parámetros de filtro conocidos de la red neuronal convolucional entrenada; recibir datos de entrada a la red neuronal convolucional entrenada; calcular una salida de cada una de la una o más capas convolucionales usando un operador convolucional Winograd con base en el factor reutilizable precalculado y los datos de entrada; y determinar datos de salida de la red convolucional entrenada con base en la salida de cada una de la una o más capas convolucionales.
MX2019004654A 2018-10-24 2018-10-24 Calculo rapido de una red neuronal convolucional. MX2019004654A (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/111655 WO2020082263A1 (en) 2018-10-24 2018-10-24 Fast computation of convolutional neural network

Publications (1)

Publication Number Publication Date
MX2019004654A true MX2019004654A (es) 2022-05-04

Family

ID=66850328

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2019004654A MX2019004654A (es) 2018-10-24 2018-10-24 Calculo rapido de una red neuronal convolucional.

Country Status (14)

Country Link
US (1) US10635951B1 (es)
EP (1) EP3662414A4 (es)
JP (1) JP6798021B1 (es)
KR (1) KR102141324B1 (es)
CN (1) CN110537193A (es)
AU (1) AU2018353930B2 (es)
BR (1) BR112019008055B1 (es)
CA (1) CA3040685C (es)
MX (1) MX2019004654A (es)
PH (1) PH12019500889A1 (es)
RU (1) RU2722473C1 (es)
SG (1) SG11201903591QA (es)
WO (1) WO2020082263A1 (es)
ZA (1) ZA201902547B (es)

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10990648B2 (en) * 2017-08-07 2021-04-27 Intel Corporation System and method for an optimized winograd convolution accelerator
US11494608B2 (en) * 2019-08-14 2022-11-08 Intel Corporation Methods and apparatus to tile walk a tensor for convolution operations
US11657282B2 (en) * 2019-09-16 2023-05-23 Qualcomm Incorporated Efficient inferencing with fast pointwise convolution
CN112766471B (zh) * 2019-11-01 2024-03-29 中科寒武纪科技股份有限公司 运算装置及相关产品
CN112784206A (zh) * 2019-11-01 2021-05-11 中科寒武纪科技股份有限公司 winograd卷积运算方法、装置、设备及存储介质
US20210216868A1 (en) * 2020-01-08 2021-07-15 Maxim Integrated Products, Inc. Systems and methods for reducing memory requirements in neural networks
CN111294512A (zh) * 2020-02-10 2020-06-16 深圳市铂岩科技有限公司 图像处理方法、装置、存储介质及摄像装置
CN111475775B (zh) * 2020-04-14 2023-09-15 腾讯科技（深圳）有限公司 图形处理器的数据处理方法、文本处理方法、装置和设备
CN111415000B (zh) * 2020-04-29 2024-03-22 Oppo广东移动通信有限公司 卷积神经网络、基于卷积神经网络的数据处理方法和装置
CN111580828B (zh) * 2020-04-30 2021-08-27 腾讯科技（深圳）有限公司 机器学习模型的编译优化方法和装置
CN111553466B (zh) * 2020-04-30 2024-03-22 上海商汤智能科技有限公司 信息处理方法、装置及设备
US11687336B2 (en) * 2020-05-08 2023-06-27 Black Sesame Technologies Inc. Extensible multi-precision data pipeline for computing non-linear and arithmetic functions in artificial neural networks
CN111767964A (zh) * 2020-07-08 2020-10-13 福州大学 基于改进的DenseNet的多通道特征重标记图像分类方法
JP2022018997A (ja) * 2020-07-17 2022-01-27 ソニーセミコンダクタソリューションズ株式会社 固体撮像素子、撮像装置、および、情報処理システム
WO2022064901A1 (ja) * 2020-09-28 2022-03-31 富士フイルム株式会社 学習済みモデル変換方法、推論方法、学習済みモデル変換装置、学習済みモデル、及び推論装置
WO2022119466A1 (en) * 2020-12-01 2022-06-09 Huawei Technologies Co., Ltd. Device and method for implementing a tensor-train decomposition operation
JP7420100B2 (ja) 2021-03-15 2024-01-23 オムロン株式会社 処理装置、処理方法、およびプログラム
KR20220162971A (ko) * 2021-06-02 2022-12-09 세메스 주식회사 데이터 처리 방법 및 데이터 비교 방법
CN117495833B (zh) * 2023-11-16 2024-05-28 广州思沛医药科技股份有限公司 一种基于大数据的脑卒中预测方法、系统及存储介质

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA2872502C (en) * 2012-05-04 2021-05-18 Rearden, Llc System and methods for coping with doppler effects in distributed-input distributed-output wireless systems
WO2016132150A1 (en) 2015-02-19 2016-08-25 Magic Pony Technology Limited Enhancing visual data using and augmenting model libraries
US10403269B2 (en) * 2015-03-27 2019-09-03 Google Llc Processing audio waveforms
CN105740894B (zh) * 2016-01-28 2020-05-29 北京航空航天大学 一种高光谱遥感图像的语义标注方法
US20170344876A1 (en) * 2016-05-31 2017-11-30 Samsung Electronics Co., Ltd. Efficient sparse parallel winograd-based convolution scheme
CN106407986B (zh) * 2016-08-29 2019-07-19 电子科技大学 一种基于深度模型的合成孔径雷达图像目标识别方法
GB2554711B (en) * 2016-10-06 2020-11-25 Imagination Tech Ltd Buffer addressing for a convolutional neural network
US10230725B2 (en) * 2016-10-24 2019-03-12 Sonicwall Inc. Edge protection for internal identity providers
US10482155B2 (en) * 2016-12-30 2019-11-19 Intel Corporation Winograd algorithm on a matrix processing architecture
RU2651147C1 (ru) * 2017-03-27 2018-04-18 Акционерное общество "ЭЛВИС-НеоТек" Устройство и способ каскадной обработки потока изображений с помощью свёрточных нейронных сетей
US10467795B2 (en) * 2017-04-08 2019-11-05 Intel Corporation Sub-graph in frequency domain and dynamic selection of convolution implementation on a GPU
CN107480707B (zh) * 2017-07-26 2020-08-07 天津大学 一种基于信息无损池化的深度神经网络方法
US10990648B2 (en) * 2017-08-07 2021-04-27 Intel Corporation System and method for an optimized winograd convolution accelerator
KR102452953B1 (ko) * 2017-10-30 2022-10-11 삼성전자주식회사 뉴럴 네트워크의 컨볼루션 연산을 수행하는 방법 및 장치
CN107844833A (zh) * 2017-11-28 2018-03-27 郑州云海信息技术有限公司 一种卷积神经网络的数据处理方法、装置及介质
US10372787B2 (en) * 2017-12-12 2019-08-06 Facebook, Inc. Hardware accelerator pre-configured with coefficients for matrix-transform operations

Also Published As

Publication number Publication date
CA3040685C (en) 2020-07-28
JP2021501377A (ja) 2021-01-14
SG11201903591QA (en) 2020-05-28
EP3662414A1 (en) 2020-06-10
AU2018353930B2 (en) 2020-10-08
KR102141324B1 (ko) 2020-08-05
CA3040685A1 (en) 2020-04-28
EP3662414A4 (en) 2020-07-22
AU2018353930A1 (en) 2020-05-14
WO2020082263A1 (en) 2020-04-30
BR112019008055B1 (pt) 2022-02-01
KR20200049695A (ko) 2020-05-08
CN110537193A (zh) 2019-12-03
BR112019008055A2 (pt) 2021-05-18
US10635951B1 (en) 2020-04-28
US20200134400A1 (en) 2020-04-30
PH12019500889A1 (en) 2019-06-17
ZA201902547B (en) 2021-02-24
JP6798021B1 (ja) 2020-12-09
RU2722473C1 (ru) 2020-06-01

Similar Documents

Publication Publication Date Title
PH12019500889A1 (en) Fast computation of a convolutional neural network
CY1123641T1 (el) Μεθοδοι και συσκευη για μια κατανεμημενη βαση δεδομενων σε ενα δικτυο
EP4312157A3 (en) Progressive neurale netzwerke
SG10201909389VA (en) Data quality analysis
SA518391000B1 (ar) منصة ذكاء الحافة ونظام تدفقات استشعار إنترنت الأشياء
MX2019005085A (es) Metodo y aparato para procesamiento de datos de cadena de bloques.
EP3276540A3 (en) Neural network method and apparatus
PH12017500471A1 (en) Systems and methods for automated data analysis and customer relationship management
MX2017009879A (es) Capas de normalizacion por lotes.
IE87469B1 (en) Image processing neural networks with separable convolutional layers
SG10201804213UA (en) Projection neural networks
EP3153996A3 (en) Method and apparatus for implementing layers on a convolutional neural network accelerator
IN2014KN02978A (es)
GB2558838A (en) Acoustic wave filter with enhanced rejection
WO2015148190A3 (en) Training, recognition, and generation in a spiking deep belief network (dbn)
AR092378A1 (es) Sistema de recomendacion agricola dirigida
MX2017008086A (es) Deteccion de objetos con red neuronal.
WO2017142397A8 (en) Device and method for generating a group equivariant convolutional neural network
EA201692294A1 (ru) Способ и устройство составления предполагаемой онтологии
AU2015364405A8 (en) Methods for simultaneous source separation
WO2020086176A8 (en) Artificial neural network and method of training an artificial neural network with epigenetic neurogenesis
MX2016010227A (es) Recomendacion de intervencion para sitios de pozo.
GB2571841A (en) Automated mutual improvement of oilfield models
WO2014122295A3 (en) Methods and systems for data cleaning
PH12019500406A1 (en) Method and device for determining key variable in model