JP7179850B2 - 畳み込みニューラル・ネットワークの完全なカーネルを近似するためのスパース・カーネルの融合 - Google Patents

畳み込みニューラル・ネットワークの完全なカーネルを近似するためのスパース・カーネルの融合 Download PDF

Info

Publication number
JP7179850B2
JP7179850B2 JP2020530640A JP2020530640A JP7179850B2 JP 7179850 B2 JP7179850 B2 JP 7179850B2 JP 2020530640 A JP2020530640 A JP 2020530640A JP 2020530640 A JP2020530640 A JP 2020530640A JP 7179850 B2 JP7179850 B2 JP 7179850B2
Authority
JP
Japan
Prior art keywords
kernel
pattern
sparse
kernels
computer
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
JP2020530640A
Other languages
English (en)
Japanese (ja)
Other versions
JP2021507345A5 (enExample
JP2021507345A (ja
Inventor
チェン、リチャード
ファン、カンフ
ピストイア、マルコ
豊太郎 鈴村
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.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
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 International Business Machines Corp filed Critical International Business Machines Corp
Publication of JP2021507345A publication Critical patent/JP2021507345A/ja
Publication of JP2021507345A5 publication Critical patent/JP2021507345A5/ja
Application granted granted Critical
Publication of JP7179850B2 publication Critical patent/JP7179850B2/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
    • G06N3/08—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
    • G06F18/2134—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis
    • G06F18/21345—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on separation criteria, e.g. independent component analysis enforcing sparsity or involving a domain transformation
    • 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
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • 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
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • 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
    • 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
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
  • Complex Calculations (AREA)
JP2020530640A 2017-12-14 2018-12-13 畳み込みニューラル・ネットワークの完全なカーネルを近似するためのスパース・カーネルの融合 Active JP7179850B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US15/841,480 US10740659B2 (en) 2017-12-14 2017-12-14 Fusing sparse kernels to approximate a full kernel of a convolutional neural network
US15/841,480 2017-12-14
PCT/IB2018/059993 WO2019116291A1 (en) 2017-12-14 2018-12-13 Fusing sparse kernels to approximate a full kernel of a convolutional neural network

Publications (3)

Publication Number Publication Date
JP2021507345A JP2021507345A (ja) 2021-02-22
JP2021507345A5 JP2021507345A5 (enExample) 2021-07-26
JP7179850B2 true JP7179850B2 (ja) 2022-11-29

Family

ID=66814568

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2020530640A Active JP7179850B2 (ja) 2017-12-14 2018-12-13 畳み込みニューラル・ネットワークの完全なカーネルを近似するためのスパース・カーネルの融合

Country Status (6)

Country Link
US (1) US10740659B2 (enExample)
JP (1) JP7179850B2 (enExample)
CN (1) CN111344720A (enExample)
DE (1) DE112018006377T5 (enExample)
GB (1) GB2583623A (enExample)
WO (1) WO2019116291A1 (enExample)

Families Citing this family (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102548718B1 (ko) * 2017-06-07 2023-06-28 삼성전자주식회사 전자 장치 및 그 제어 방법
US12393829B2 (en) * 2019-07-25 2025-08-19 Samsung Electronics Co., Ltd. Methods and systems with convolutional neural network (CNN) performance
US11144290B2 (en) 2019-09-13 2021-10-12 Huawei Technologies Co., Ltd. Method and apparatus for enabling autonomous acceleration of dataflow AI applications
US12265911B2 (en) * 2020-02-06 2025-04-01 Google Llc Neural network layers with a controlled degree of spatial invariance
US20210256385A1 (en) * 2020-02-14 2021-08-19 Northeastern University Computer-implemented methods and systems for dnn weight pruning for real-time execution on mobile devices
US11379951B2 (en) * 2020-03-25 2022-07-05 Nintendo Co., Ltd. Systems and methods for machine learned image conversion
US11494875B2 (en) 2020-03-25 2022-11-08 Nintendo Co., Ltd. Systems and methods for machine learned image conversion
CN113344199B (zh) * 2021-06-17 2024-05-03 阿波罗智联(北京)科技有限公司 用于训练可分离卷积网络的方法、路侧设备及云控平台
US20230004800A1 (en) * 2021-07-04 2023-01-05 Numenta, Inc. Complementary sparsity in processing tensors
US20250138820A1 (en) * 2023-10-26 2025-05-01 Etched.ai, Inc. Model-specific asic compilation using fused kernel replacement

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014535118A (ja) 2011-11-09 2014-12-25 クゥアルコム・インコーポレイテッドＱｕａｌｃｏｍｍ Ｉｎｃｏｒｐｏｒａｔｅｄ 無監督ニューラルリプレイ、学習改善、関連付け、およびメモリ転送のための方法および装置：ニューラル構成要素メモリ転送
WO2016197026A1 (en) 2015-06-05 2016-12-08 Sony Corporation Full reference image quality assessment based on convolutional neural network
US20170103308A1 (en) 2015-10-08 2017-04-13 International Business Machines Corporation Acceleration of convolutional neural network training using stochastic perforation

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104077612B (zh) * 2014-07-15 2017-09-22 中国科学院合肥物质科学研究院 一种基于多特征稀疏表示技术的害虫图像识别方法
US9652817B2 (en) 2015-03-12 2017-05-16 Samsung Electronics Co., Ltd. Automated compute kernel fusion, resizing, and interleave
CN105046193B (zh) * 2015-06-05 2018-07-10 上海大学 一种基于融合稀疏表示矩阵的人体动作识别方法
US9972063B2 (en) 2015-07-30 2018-05-15 International Business Machines Corporation Pipelined approach to fused kernels for optimization of machine learning workloads on graphical processing units
US9904874B2 (en) 2015-11-05 2018-02-27 Microsoft Technology Licensing, Llc Hardware-efficient deep convolutional neural networks
CN108701210B (zh) 2016-02-02 2021-08-17 北京市商汤科技开发有限公司 用于cnn网络适配和对象在线追踪的方法和系统
US10181188B2 (en) * 2016-02-19 2019-01-15 International Business Machines Corporation Structure-preserving composite model for skin lesion segmentation
US10832136B2 (en) 2016-05-18 2020-11-10 Nec Corporation Passive pruning of filters in a convolutional neural network
CN107330463B (zh) 2017-06-29 2020-12-08 南京信息工程大学 基于cnn多特征联合和多核稀疏表示的车型识别方法

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014535118A (ja) 2011-11-09 2014-12-25 クゥアルコム・インコーポレイテッドＱｕａｌｃｏｍｍ Ｉｎｃｏｒｐｏｒａｔｅｄ 無監督ニューラルリプレイ、学習改善、関連付け、およびメモリ転送のための方法および装置：ニューラル構成要素メモリ転送
WO2016197026A1 (en) 2015-06-05 2016-12-08 Sony Corporation Full reference image quality assessment based on convolutional neural network
US20170103308A1 (en) 2015-10-08 2017-04-13 International Business Machines Corporation Acceleration of convolutional neural network training using stochastic perforation

Also Published As

Publication number Publication date
US20190188526A1 (en) 2019-06-20
GB2583623A (en) 2020-11-04
CN111344720A (zh) 2020-06-26
WO2019116291A1 (en) 2019-06-20
US10740659B2 (en) 2020-08-11
JP2021507345A (ja) 2021-02-22
DE112018006377T5 (de) 2020-08-20
GB202010475D0 (en) 2020-08-19

Similar Documents

Publication Publication Date Title
JP7179850B2 (ja) 畳み込みニューラル・ネットワークの完全なカーネルを近似するためのスパース・カーネルの融合
Li et al. Cross-modal weighting network for RGB-D salient object detection
EP3612933B1 (en) Enhancing processing performance of artificial intelligence/machine hardware by data sharing and distribution as well as reuse of data in neuron buffer/line buffer
KR102856911B1 (ko) 신경망의 기능적 부분망의 동시 훈련
US12169782B2 (en) Dynamic precision scaling at epoch granularity in neural networks
JP7513358B2 (ja) 機械学習モデルを堅牢化するための学習入力のプリプロセッシング
CN108229655A (zh) 卷积神经网络（cnn）处理方法和设备
JP2021504837A (ja) 重み行列への空間的局所性を強化すること、および周波数圧縮をもたらすことを通した、完全接続型／回帰型深層ネットワークの圧縮
CN107944545A (zh) 应用于神经网络的计算方法及计算装置
US11989897B2 (en) Depth map generation from sparse depth samples in an augmented reality environment
JP7372011B2 (ja) 深層学習の大規模なモデル・サポート
KR20210014561A (ko) 다수 컨벌루션 윈도우 중의 이미지 데이터를 추출하는 방법, 장치, 기기 및 컴퓨터 판독 가능한 저장매체
US10565285B2 (en) Processor and memory transparent convolutional lowering and auto zero padding for deep neural network implementations
CN111709415A (zh) 目标检测方法、装置、计算机设备和存储介质
US10936938B2 (en) Method for visualizing neural network models
Lu et al. Enhancing small target traffic sign detection with ML_SAP in YOLOv5s
CN115145391A (zh) 一种基于ai深度学习的虚拟现实跑步机自适应方法及系统
US20220036245A1 (en) EXTRACTING SEQUENCES FROM d-DIMENSIONAL INPUT DATA FOR SEQUENTIAL PROCESSING WITH NEURAL NETWORKS
US12412114B2 (en) Visualization scheme of noise in a quantum circuit
US20200026963A1 (en) Reducing computational costs of deep reinforcement learning by gated convolutional neural network
US11562003B2 (en) Representing search results via a three-dimensional matrix
US12400137B1 (en) Bidirectional network on a data-flow centric processor
Mi et al. Semantics recalibration and detail enhancement network for real‐time semantic segmentation
US20240143982A1 (en) Fused Convolutions for Fast Deep Neural Network
US20250181991A1 (en) Feature dimensionality reduction for machine learning models

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20210518

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20210525

RD04 Notification of resignation of power of attorney

Free format text: JAPANESE INTERMEDIATE CODE: A7424

Effective date: 20220502

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20220524

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20220531

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20220818

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: 20221108

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20221116

R150 Certificate of patent or registration of utility model

Ref document number: 7179850

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150