MX2021011131A - Compresion de red neuronal profunda basada en rango de bajo desplazamiento. - Google Patents

Compresion de red neuronal profunda basada en rango de bajo desplazamiento.

Info

Publication number
MX2021011131A
MX2021011131A MX2021011131A MX2021011131A MX2021011131A MX 2021011131 A MX2021011131 A MX 2021011131A MX 2021011131 A MX2021011131 A MX 2021011131A MX 2021011131 A MX2021011131 A MX 2021011131A MX 2021011131 A MX2021011131 A MX 2021011131A
Authority
MX
Mexico
Prior art keywords
neural network
deep neural
low displacement
rank based
matrices
Prior art date
Application number
MX2021011131A
Other languages
English (en)
Inventor
Fabien Racape
Swayambhoo Jain
Shahab Hamidi-Rad
Dimitris Papadimitriou
Original Assignee
Interdigital Vc Holdings Inc
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 Interdigital Vc Holdings Inc filed Critical Interdigital Vc Holdings Inc
Publication of MX2021011131A publication Critical patent/MX2021011131A/es

Links

Classifications

    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)
  • Image Processing (AREA)

Abstract

Un método y un aparato para llevar a cabo compresión de red neuronal profunda utilizan una serie de entrenamiento de aproximación junto con información, tal como en matrices representando ponderaciones, inclinaciones y no linealidades, para comprimir iterativamente una red neuronal profunda pre-entrenada por aproximación basada en rango de bajo desplazamiento de las matrices de ponderación de estrato de red. La aproximación de rango de bajo desplazamiento permite el reemplazo de matrices de ponderación de un estrato original de la red neuronal profunda pre-entrenada como la suma de un número pequeño de matrices estructuradas, permitiendo compresión y complejidad de inferencia baja.
MX2021011131A 2019-03-15 2020-03-13 Compresion de red neuronal profunda basada en rango de bajo desplazamiento. MX2021011131A (es)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US201962818914P 2019-03-15 2019-03-15
PCT/US2020/022585 WO2020190696A1 (en) 2019-03-15 2020-03-13 Low displacement rank based deep neural network compression

Publications (1)

Publication Number Publication Date
MX2021011131A true MX2021011131A (es) 2021-10-14

Family

ID=70228824

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2021011131A MX2021011131A (es) 2019-03-15 2020-03-13 Compresion de red neuronal profunda basada en rango de bajo desplazamiento.

Country Status (6)

Country Link
US (1) US20220188633A1 (es)
EP (1) EP3939301A1 (es)
JP (1) JP7575388B2 (es)
CN (1) CN113574887B (es)
MX (1) MX2021011131A (es)
WO (1) WO2020190696A1 (es)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11037330B2 (en) * 2017-04-08 2021-06-15 Intel Corporation Low rank matrix compression
US11700518B2 (en) * 2019-05-31 2023-07-11 Huawei Technologies Co., Ltd. Methods and systems for relaying feature-driven communications
US20210326710A1 (en) * 2020-04-16 2021-10-21 Tencent America LLC Neural network model compression
WO2022087953A1 (zh) * 2020-10-29 2022-05-05 华为技术有限公司 一种基于神经网络模型的量化方法及其相关设备
US11818399B2 (en) * 2021-01-04 2023-11-14 Tencent America LLC Techniques for signaling neural network topology and parameters in the coded video stream
CN112836801A (zh) * 2021-02-03 2021-05-25 上海商汤智能科技有限公司 深度学习网络确定方法、装置、电子设备及存储介质

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1520580A (zh) * 2000-07-06 2004-08-11 ŦԼ�и��ױ��Ǵ�ѧ�йܻ� 用于增强数据解析度的方法和设备
US7133568B2 (en) * 2000-08-04 2006-11-07 Nikitin Alexei V Method and apparatus for analysis of variables
US10515307B2 (en) * 2015-06-05 2019-12-24 Google Llc Compressed recurrent neural network models
US10681380B2 (en) 2015-06-12 2020-06-09 Panasonic Intellectual Property Management Co., Ltd. Image encoding method, image decoding method, image encoding apparatus, and image decoding apparatus
US11321609B2 (en) * 2016-10-19 2022-05-03 Samsung Electronics Co., Ltd Method and apparatus for neural network quantization
US12079700B2 (en) * 2016-10-26 2024-09-03 Google Llc Structured orthogonal random features for kernel-based machine learning
US10599935B2 (en) 2017-02-22 2020-03-24 Arm Limited Processing artificial neural network weights
US11037330B2 (en) * 2017-04-08 2021-06-15 Intel Corporation Low rank matrix compression
SG11201911600VA (en) 2017-07-07 2020-01-30 Mitsubishi Electric Corp Data processing device, data processing method, and compressed data
EP3451293A1 (en) * 2017-08-28 2019-03-06 Thomson Licensing Method and apparatus for filtering with multi-branch deep learning
CN107396124B (zh) * 2017-08-29 2019-09-20 南京大学 基于深度神经网络的视频压缩方法
US11429849B2 (en) * 2018-05-11 2022-08-30 Intel Corporation Deep compressed network

Also Published As

Publication number Publication date
EP3939301A1 (en) 2022-01-19
WO2020190696A1 (en) 2020-09-24
JP2022525392A (ja) 2022-05-13
CN113574887A (zh) 2021-10-29
US20220188633A1 (en) 2022-06-16
CN113574887B (zh) 2024-09-27
JP7575388B2 (ja) 2024-10-29

Similar Documents

Publication Publication Date Title
MX2021011131A (es) Compresion de red neuronal profunda basada en rango de bajo desplazamiento.
GB2600871A (en) Machine learning hardware having reduced precision parameter components for efficient parameter update
JP2021505993A5 (es)
WO2019113502A8 (en) Adding deep learning based ai control
EP4113354A3 (en) Method and apparatus for generating pre-trained language model, electronic device and storage medium
SG11202008322UA (en) Neural network model training method and apparatus, computer device, and storage medium
WO2022126797A1 (zh) 基于多层级知识蒸馏预训练语言模型自动压缩方法及平台
MY195878A (en) System And Method For Training Neural Networks
CN111898020B (zh) 基于bert和lstm的知识学习体系推荐方法、设备及介质
JP2020038704A5 (es)
MY182749A (en) Semi-supervised learning for training an ensemble of deep convolutional neural networks
CN109583621A (zh) 一种基于改进变分模态分解的pso-lssvm短期负荷预测方法
GB2590768A8 (en) Method for optimizing motion parameter of industrial robot for energy saving in big data environment
CN115223049B (zh) 面向电力场景边缘计算大模型压缩的知识蒸馏与量化方法
CN106951473A (zh) 面向视觉障碍人士的深度视觉问答系统的构建方法
EP3859588A3 (en) Method, apparatus, device and medium for generating recruitment position description text
CN105976282A (zh) 一种试题难度量化方法及系统
GB2610319A (en) Automatic compression method and platform for multilevel knowledge distillation-based pre-trained language model
CN109740737A (zh) 卷积神经网络量化处理方法、装置及计算机设备
EP4099333A3 (en) Method and apparatus for training compound property prediction model, storage medium and computer program product
WO2021246892A8 (en) Method for training an artificial neural network comprising quantized parameters
WO2022075678A3 (ko) 의사 정상 데이터를 이용한 자가 감독 학습 기반의 차량 이상징후 탐지 장치 및 방법
CN102676634A (zh) 一种气调包装生鲜冷却牛肉腐败菌生长预测方法
Zili et al. Forecasting Indonesian mortality rates using the Lee-Carter model and ARIMA method
GB2615472A (en) Geological property modeling with neural network representations