DE112018006377T5 - Verschmelzen spärlich besetzter kernels zur approximation eines vollen kernels eines neuronalen faltungsnetzes - Google Patents

Verschmelzen spärlich besetzter kernels zur approximation eines vollen kernels eines neuronalen faltungsnetzes Download PDF

Info

Publication number
DE112018006377T5
DE112018006377T5 DE112018006377.1T DE112018006377T DE112018006377T5 DE 112018006377 T5 DE112018006377 T5 DE 112018006377T5 DE 112018006377 T DE112018006377 T DE 112018006377T DE 112018006377 T5 DE112018006377 T5 DE 112018006377T5
Authority
DE
Germany
Prior art keywords
kernel
complementary
pattern
computer
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.)
Pending
Application number
DE112018006377.1T
Other languages
German (de)
English (en)
Inventor
Richard Chen
Quanfu Fan
Marco Pistoia
Toyotaro Suzumura
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 DE112018006377T5 publication Critical patent/DE112018006377T5/de
Pending legal-status Critical Current

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)
DE112018006377.1T 2017-12-14 2018-12-13 Verschmelzen spärlich besetzter kernels zur approximation eines vollen kernels eines neuronalen faltungsnetzes Pending DE112018006377T5 (de)

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 (1)

Publication Number Publication Date
DE112018006377T5 true DE112018006377T5 (de) 2020-08-20

Family

ID=66814568

Family Applications (1)

Application Number Title Priority Date Filing Date
DE112018006377.1T Pending DE112018006377T5 (de) 2017-12-14 2018-12-13 Verschmelzen spärlich besetzter kernels zur approximation eines vollen kernels eines neuronalen faltungsnetzes

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

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9424513B2 (en) * 2011-11-09 2016-08-23 Qualcomm Incorporated Methods and apparatus for neural component memory transfer of a referenced pattern by including neurons to output a pattern substantially the same as the referenced pattern
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
US9741107B2 (en) * 2015-06-05 2017-08-22 Sony Corporation Full reference image quality assessment based on convolutional neural network
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
US10380479B2 (en) 2015-10-08 2019-08-13 International Business Machines Corporation Acceleration of convolutional neural network training using stochastic perforation
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

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
JP7179850B2 (ja) 2022-11-29
US10740659B2 (en) 2020-08-11
JP2021507345A (ja) 2021-02-22
GB202010475D0 (en) 2020-08-19

Similar Documents

Publication Publication Date Title
DE112018006377T5 (de) Verschmelzen spärlich besetzter kernels zur approximation eines vollen kernels eines neuronalen faltungsnetzes
DE69217047T2 (de) Verbesserungen in neuronalnetzen
DE19581638C2 (de) Rechenvorrichtung mit einem Mikroprozessor, einem neuralen Netz-Koprozessor und einer DMA-Steuervorrichtung
DE112018004693T5 (de) Verbessern der effizienz eines neuronalen netzes
DE102018111905A1 (de) Domänenspezifische Sprache zur Erzeugung rekurrenter neuronaler Netzarchitekturen
DE102020002964A1 (de) Verwenden eines neuronalen Netzwerks mit einer Zwei-Strom Encoder-Architektur zur Erzeugung digitaler Kompositbilder
DE102019130702A1 (de) Stilbasierte architektur für generative neuronale netzwerke
DE102018126342A1 (de) Transformieren von faltenden neuronalen netzen zum lernen von visuellen sequenzen
DE102019007196A1 (de) Identifizieren von Zielobjekten unter Nutzung der skalierungsdiversen Segmentierung dienender neuronaler Netzwerke
DE102020215942A1 (de) System und verfahren für unüberwachte domänenanpassung mit mischungstraining
DE202016008658U1 (de) Bildklassifikationsneuronalnetze
DE112021002867T5 (de) Defektdetektion für eine leiterplattenbaugruppe
DE112019003326T5 (de) Speichererweiterte neuronale netzwerkarchitekturen eines codierers-decodierers
DE102021107510A1 (de) Training eines neuronalen netzwerks unter speicherbeschränkung
DE112020003105T5 (de) Schicht für schicht-debugging von neuronalen netzwerken
DE112019004391T5 (de) Grossmodellunterstützung für deep learning
DE102021124264A1 (de) Erzeugung von synthetischen Systemfehlern
DE112019000676T5 (de) Zentraler scheduler und anweisungszuteiler für einen neuronalen inferenzprozessor
DE102017005964A1 (de) Techniken zum Auswählen von Objekten in Bildern
DE112021006273T5 (de) Automatische beschreibung und entnahme von tabellendaten im portable document format unter verwendung von neuronalen graphennetzen
DE102023120640A1 (de) Gestaltete glyphen vermittels generativer ki
DE112021003003T5 (de) Kontinuierliches lernen mit querverbindungen
DE112020005732T5 (de) Erzeugen von trainingsdaten zur objekterkennung
DE112021000308T5 (de) Graphenfaltungsnetze für video-grounding
DE112021002868T5 (de) Erzeugung von rich descriptor framework zu text unter verwendung vongraphen und strukturellen neuronalen codierern

Legal Events

Date Code Title Description
R012 Request for examination validly filed
R084 Declaration of willingness to licence