CN107239825B - 考虑负载均衡的深度神经网络压缩方法 - Google Patents
考虑负载均衡的深度神经网络压缩方法 Download PDFInfo
- Publication number
- CN107239825B CN107239825B CN201611105081.7A CN201611105081A CN107239825B CN 107239825 B CN107239825 B CN 107239825B CN 201611105081 A CN201611105081 A CN 201611105081A CN 107239825 B CN107239825 B CN 107239825B
- Authority
- CN
- China
- Prior art keywords
- matrix
- neural network
- sub
- compression
- training
- 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
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 130
- 238000007906 compression Methods 0.000 title claims abstract description 128
- 230000006835 compression Effects 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 70
- 239000011159 matrix material Substances 0.000 claims abstract description 188
- 230000000903 blocking effect Effects 0.000 claims abstract description 24
- 210000002569 neuron Anatomy 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 68
- 238000004364 calculation method Methods 0.000 claims description 26
- 238000013138 pruning Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 15
- 230000035945 sensitivity Effects 0.000 claims description 14
- 238000010206 sensitivity analysis Methods 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 description 27
- 239000013598 vector Substances 0.000 description 21
- 239000010410 layer Substances 0.000 description 17
- 230000002829 reductive effect Effects 0.000 description 14
- 238000012360 testing method Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 238000012669 compression test Methods 0.000 description 8
- 230000001133 acceleration Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000000717 retained effect Effects 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000015654 memory Effects 0.000 description 4
- 238000011084 recovery Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000000638 solvent extraction Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000002790 cross-validation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000005284 excitation Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000000306 recurrent effect Effects 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 238000009966 trimming Methods 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000005056 compaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000002356 single layer Substances 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
Images
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
- G06N3/04—Architecture, e.g. interconnection topology
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/10—Network architectures or network communication protocols for network security for controlling access to devices or network resources
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/06—Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice
- G10L15/063—Training
-
- 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
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/08—Speech classification or search
- G10L15/16—Speech classification or search using artificial neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Neurology (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Complex Calculations (AREA)
- Memory System (AREA)
Abstract
Description
Claims (17)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/390,556 US10984308B2 (en) | 2016-08-12 | 2016-12-26 | Compression method for deep neural networks with load balance |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/242,624 US20180046903A1 (en) | 2016-08-12 | 2016-08-22 | Deep processing unit (dpu) for implementing an artificial neural network (ann) |
US15/242,622 US10621486B2 (en) | 2016-08-12 | 2016-08-22 | Method for optimizing an artificial neural network (ANN) |
US15/242,624 | 2016-08-22 | ||
US15/242,622 | 2016-08-22 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107239825A CN107239825A (zh) | 2017-10-10 |
CN107239825B true CN107239825B (zh) | 2021-04-09 |
Family
ID=59983010
Family Applications (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611105480.3A Active CN107679617B (zh) | 2016-08-12 | 2016-12-05 | 多次迭代的深度神经网络压缩方法 |
CN201611105491.1A Active CN107689948B (zh) | 2016-08-12 | 2016-12-05 | 应用于神经网络硬件加速系统的高效数据访存管理装置 |
CN201611104482.0A Active CN107689224B (zh) | 2016-08-12 | 2016-12-05 | 合理使用掩码的深度神经网络压缩方法 |
CN201611105081.7A Active CN107239825B (zh) | 2016-08-12 | 2016-12-05 | 考虑负载均衡的深度神经网络压缩方法 |
Family Applications Before (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611105480.3A Active CN107679617B (zh) | 2016-08-12 | 2016-12-05 | 多次迭代的深度神经网络压缩方法 |
CN201611105491.1A Active CN107689948B (zh) | 2016-08-12 | 2016-12-05 | 应用于神经网络硬件加速系统的高效数据访存管理装置 |
CN201611104482.0A Active CN107689224B (zh) | 2016-08-12 | 2016-12-05 | 合理使用掩码的深度神经网络压缩方法 |
Country Status (1)
Country | Link |
---|---|
CN (4) | CN107679617B (zh) |
Families Citing this family (67)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102017218889A1 (de) * | 2017-10-23 | 2019-04-25 | Robert Bosch Gmbh | Unscharf parametriertes KI-Modul sowie Verfahren zum Betreiben |
US11651223B2 (en) * | 2017-10-27 | 2023-05-16 | Baidu Usa Llc | Systems and methods for block-sparse recurrent neural networks |
CN107977704B (zh) * | 2017-11-10 | 2020-07-31 | 中国科学院计算技术研究所 | 权重数据存储方法和基于该方法的神经网络处理器 |
CN107832835A (zh) * | 2017-11-14 | 2018-03-23 | 贵阳海信网络科技有限公司 | 一种卷积神经网络的轻量化方法及装置 |
CN107832439B (zh) | 2017-11-16 | 2019-03-08 | 百度在线网络技术(北京)有限公司 | 多轮状态追踪的方法、系统及终端设备 |
CN109902812B (zh) * | 2017-12-11 | 2020-10-09 | 中科寒武纪科技股份有限公司 | 板卡和神经网络运算方法 |
CN108170529A (zh) * | 2017-12-26 | 2018-06-15 | 北京工业大学 | 一种基于长短期记忆网络的云数据中心负载预测方法 |
CN108038546B (zh) | 2017-12-29 | 2021-02-09 | 百度在线网络技术(北京)有限公司 | 用于压缩神经网络的方法和装置 |
CN109791628B (zh) * | 2017-12-29 | 2022-12-27 | 清华大学 | 神经网络模型分块压缩方法、训练方法、计算装置及系统 |
EP3624019A4 (en) | 2017-12-30 | 2021-03-24 | Cambricon Technologies Corporation Limited | CHIP DEVICE WITH INTEGRATED CIRCUIT AND ASSOCIATED PRODUCT |
CN109993292B (zh) * | 2017-12-30 | 2020-08-04 | 中科寒武纪科技股份有限公司 | 集成电路芯片装置及相关产品 |
CN109993291B (zh) * | 2017-12-30 | 2020-07-07 | 中科寒武纪科技股份有限公司 | 集成电路芯片装置及相关产品 |
CN109993290B (zh) | 2017-12-30 | 2021-08-06 | 中科寒武纪科技股份有限公司 | 集成电路芯片装置及相关产品 |
CN113807510B (zh) | 2017-12-30 | 2024-05-10 | 中科寒武纪科技股份有限公司 | 集成电路芯片装置及相关产品 |
CN108280514B (zh) * | 2018-01-05 | 2020-10-16 | 中国科学技术大学 | 基于fpga的稀疏神经网络加速系统和设计方法 |
CN110084364B (zh) * | 2018-01-25 | 2021-08-27 | 赛灵思电子科技(北京)有限公司 | 一种深度神经网络压缩方法和装置 |
CN110110853B (zh) * | 2018-02-01 | 2021-07-30 | 赛灵思电子科技(北京)有限公司 | 一种深度神经网络压缩方法、装置及计算机可读介质 |
EP3750113A1 (en) * | 2018-02-09 | 2020-12-16 | DeepMind Technologies Limited | Contiguous sparsity pattern neural networks |
CN110197262B (zh) * | 2018-02-24 | 2021-07-30 | 赛灵思电子科技(北京)有限公司 | 用于lstm网络的硬件加速器 |
CN108540338B (zh) * | 2018-03-08 | 2021-08-31 | 西安电子科技大学 | 基于深度循环神经网络的应用层通信协议识别的方法 |
CN108510063B (zh) * | 2018-04-08 | 2020-03-20 | 清华大学 | 一种应用于卷积神经网络的加速方法和加速器 |
WO2019219846A1 (en) * | 2018-05-17 | 2019-11-21 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Concepts for distributed learning of neural networks and/or transmission of parameterization updates therefor |
CN110797021B (zh) * | 2018-05-24 | 2022-06-07 | 腾讯科技(深圳)有限公司 | 混合语音识别网络训练方法、混合语音识别方法、装置及存储介质 |
CN108665067B (zh) * | 2018-05-29 | 2020-05-29 | 北京大学 | 用于深度神经网络频繁传输的压缩方法及系统 |
US10832139B2 (en) * | 2018-06-22 | 2020-11-10 | Moffett Technologies Co. Limited | Neural network acceleration and embedding compression systems and methods with activation sparsification |
CN109102064B (zh) * | 2018-06-26 | 2020-11-13 | 杭州雄迈集成电路技术股份有限公司 | 一种高精度的神经网络量化压缩方法 |
CN110659731B (zh) * | 2018-06-30 | 2022-05-17 | 华为技术有限公司 | 一种神经网络训练方法及装置 |
CN109063835B (zh) * | 2018-07-11 | 2021-07-09 | 中国科学技术大学 | 神经网络的压缩装置及方法 |
EP3690679A4 (en) | 2018-08-06 | 2021-02-17 | Huawei Technologies Co., Ltd. | MATRIX PROCESSING PROCESS AND APPARATUS, AND LOGIC CIRCUIT |
CN110874550A (zh) * | 2018-08-31 | 2020-03-10 | 华为技术有限公司 | 数据处理方法、装置、设备和系统 |
WO2020062312A1 (zh) * | 2018-09-30 | 2020-04-02 | 华为技术有限公司 | 信号处理装置和信号处理方法 |
CN109104197B (zh) * | 2018-11-12 | 2022-02-11 | 合肥工业大学 | 应用于卷积神经网络的非还原稀疏数据的编译码电路及其编译码方法 |
CN111382852B (zh) * | 2018-12-28 | 2022-12-09 | 上海寒武纪信息科技有限公司 | 数据处理装置、方法、芯片及电子设备 |
CN111291884A (zh) * | 2018-12-10 | 2020-06-16 | 中科寒武纪科技股份有限公司 | 神经网络剪枝方法、装置、电子设备及计算机可读介质 |
CN111353591A (zh) * | 2018-12-20 | 2020-06-30 | 中科寒武纪科技股份有限公司 | 一种计算装置及相关产品 |
CN111383157B (zh) * | 2018-12-29 | 2023-04-14 | 北京市商汤科技开发有限公司 | 图像处理方法、装置、车载运算平台、电子设备及系统 |
CN113168554B (zh) * | 2018-12-29 | 2023-11-28 | 华为技术有限公司 | 一种神经网络压缩方法及装置 |
CN109800869B (zh) * | 2018-12-29 | 2021-03-05 | 深圳云天励飞技术有限公司 | 数据压缩方法及相关装置 |
CN109784490B (zh) * | 2019-02-02 | 2020-07-03 | 北京地平线机器人技术研发有限公司 | 神经网络的训练方法、装置和电子设备 |
CN111626305B (zh) * | 2019-02-28 | 2023-04-18 | 阿里巴巴集团控股有限公司 | 目标检测方法、装置和设备 |
CN109938696A (zh) * | 2019-03-22 | 2019-06-28 | 江南大学 | 神经电信号压缩感知处理方法及电路 |
CN109978144B (zh) * | 2019-03-29 | 2021-04-13 | 联想(北京)有限公司 | 一种模型压缩方法和系统 |
CN110399972B (zh) * | 2019-07-22 | 2021-05-25 | 上海商汤智能科技有限公司 | 数据处理方法、装置及电子设备 |
CN110704024B (zh) * | 2019-09-28 | 2022-03-08 | 中昊芯英(杭州)科技有限公司 | 一种矩阵处理装置、方法及处理设备 |
CN110705996B (zh) * | 2019-10-17 | 2022-10-11 | 支付宝(杭州)信息技术有限公司 | 基于特征掩码的用户行为识别方法、系统、及装置 |
CN112699990B (zh) * | 2019-10-22 | 2024-06-07 | 杭州海康威视数字技术股份有限公司 | 神经网络模型训练方法、装置及电子设备 |
CN111078840B (zh) * | 2019-12-20 | 2022-04-08 | 浙江大学 | 一种基于文档向量的电影评论情感分析方法 |
CN111126600A (zh) * | 2019-12-20 | 2020-05-08 | 上海寒武纪信息科技有限公司 | 神经网络模型的训练方法、数据处理方法和相关产品 |
US20210209462A1 (en) * | 2020-01-07 | 2021-07-08 | Alibaba Group Holding Limited | Method and system for processing a neural network |
KR20210106131A (ko) | 2020-02-20 | 2021-08-30 | 삼성전자주식회사 | 전자 장치 및 그의 제어 방법 |
CN115280272A (zh) * | 2020-04-03 | 2022-11-01 | 北京希姆计算科技有限公司 | 数据存取电路和方法 |
KR20210126398A (ko) * | 2020-04-10 | 2021-10-20 | 에스케이하이닉스 주식회사 | 시스톨릭 어레이를 갖는 신경망 연산 장치 |
CN111711511B (zh) * | 2020-06-16 | 2021-07-13 | 电子科技大学 | 频域数据有损压缩方法 |
CN111553471A (zh) * | 2020-07-13 | 2020-08-18 | 北京欣奕华数字科技有限公司 | 一种数据分析处理方法及装置 |
CN112132062B (zh) * | 2020-09-25 | 2021-06-29 | 中南大学 | 一种基于剪枝压缩神经网络的遥感图像分类方法 |
CN112286447A (zh) * | 2020-10-14 | 2021-01-29 | 天津津航计算技术研究所 | 一种新型软件硬件协同raid改进系统 |
CN112230851A (zh) * | 2020-10-14 | 2021-01-15 | 天津津航计算技术研究所 | 一种新型软件硬件协同raid改进方法 |
CN112270352A (zh) * | 2020-10-26 | 2021-01-26 | 中山大学 | 一种基于并行剪枝优化的决策树生成方法及装置 |
CN112396178A (zh) * | 2020-11-12 | 2021-02-23 | 江苏禹空间科技有限公司 | 一种提高cnn网络压缩效率的方法 |
WO2022133623A1 (en) * | 2020-12-24 | 2022-06-30 | Intel Corporation | Accelerated scale-out performance of deep learning training workload with embedding tables |
CN112883982B (zh) * | 2021-01-08 | 2023-04-18 | 西北工业大学 | 一种面向神经网络稀疏特征的数据去零编码及封装方法 |
US20220343145A1 (en) * | 2021-04-21 | 2022-10-27 | Alibaba Singapore Holding Private Limited | Method and system for graph neural network acceleration |
CN113794709B (zh) * | 2021-09-07 | 2022-06-24 | 北京理工大学 | 一种用于二值稀疏矩阵的混合编码方法 |
CN113947185B (zh) * | 2021-09-30 | 2022-11-18 | 北京达佳互联信息技术有限公司 | 任务处理网络生成、任务处理方法、装置、电子设备及存储介质 |
CN116187408B (zh) * | 2023-04-23 | 2023-07-21 | 成都甄识科技有限公司 | 稀疏加速单元、计算方法及稀疏神经网络硬件加速系统 |
CN117170588B (zh) * | 2023-11-01 | 2024-01-26 | 北京壁仞科技开发有限公司 | 用于对张量数据的布局进行转换的方法、设备和介质 |
CN117634711B (zh) * | 2024-01-25 | 2024-05-14 | 北京壁仞科技开发有限公司 | 张量维度切分方法、系统、设备和介质 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105184369A (zh) * | 2015-09-08 | 2015-12-23 | 杭州朗和科技有限公司 | 用于深度学习模型的矩阵压缩方法和装置 |
CN105260794A (zh) * | 2015-10-12 | 2016-01-20 | 上海交通大学 | 一种云数据中心的负载预测方法 |
CN105593843A (zh) * | 2013-08-30 | 2016-05-18 | 微软技术许可有限责任公司 | 稀疏矩阵数据结构 |
Family Cites Families (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1997044743A1 (de) * | 1996-05-23 | 1997-11-27 | Siemens Aktiengesellschaft | Verfahren zur optimierung eines fuzzy-regelsatzes durch einen rechner |
CN102129397A (zh) * | 2010-12-29 | 2011-07-20 | 深圳市永达电子股份有限公司 | 一种自适应磁盘阵列故障预测方法及系统 |
US9053430B2 (en) * | 2012-11-19 | 2015-06-09 | Qualcomm Incorporated | Method and apparatus for inferring logical dependencies between random processes |
US9400955B2 (en) * | 2013-12-13 | 2016-07-26 | Amazon Technologies, Inc. | Reducing dynamic range of low-rank decomposition matrices |
US20150206050A1 (en) * | 2014-01-23 | 2015-07-23 | Qualcomm Incorporated | Configuring neural network for low spiking rate |
US9324321B2 (en) * | 2014-03-07 | 2016-04-26 | Microsoft Technology Licensing, Llc | Low-footprint adaptation and personalization for a deep neural network |
US9202178B2 (en) * | 2014-03-11 | 2015-12-01 | Sas Institute Inc. | Computerized cluster analysis framework for decorrelated cluster identification in datasets |
US10242313B2 (en) * | 2014-07-18 | 2019-03-26 | James LaRue | Joint proximity association template for neural networks |
CN104217433B (zh) * | 2014-08-29 | 2017-06-06 | 华为技术有限公司 | 一种分析图像的方法及装置 |
CN104915322B (zh) * | 2015-06-09 | 2018-05-01 | 中国人民解放军国防科学技术大学 | 一种卷积神经网络硬件加速方法 |
CN105184362B (zh) * | 2015-08-21 | 2018-02-02 | 中国科学院自动化研究所 | 基于参数量化的深度卷积神经网络的加速与压缩方法 |
-
2016
- 2016-12-05 CN CN201611105480.3A patent/CN107679617B/zh active Active
- 2016-12-05 CN CN201611105491.1A patent/CN107689948B/zh active Active
- 2016-12-05 CN CN201611104482.0A patent/CN107689224B/zh active Active
- 2016-12-05 CN CN201611105081.7A patent/CN107239825B/zh active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105593843A (zh) * | 2013-08-30 | 2016-05-18 | 微软技术许可有限责任公司 | 稀疏矩阵数据结构 |
CN105184369A (zh) * | 2015-09-08 | 2015-12-23 | 杭州朗和科技有限公司 | 用于深度学习模型的矩阵压缩方法和装置 |
CN105260794A (zh) * | 2015-10-12 | 2016-01-20 | 上海交通大学 | 一种云数据中心的负载预测方法 |
Also Published As
Publication number | Publication date |
---|---|
CN107679617B (zh) | 2021-04-09 |
CN107679617A (zh) | 2018-02-09 |
CN107689224B (zh) | 2020-09-01 |
CN107239825A (zh) | 2017-10-10 |
CN107689948B (zh) | 2020-09-01 |
CN107689948A (zh) | 2018-02-13 |
CN107689224A (zh) | 2018-02-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107239825B (zh) | 考虑负载均衡的深度神经网络压缩方法 | |
CN107729999B (zh) | 考虑矩阵相关性的深度神经网络压缩方法 | |
US10984308B2 (en) | Compression method for deep neural networks with load balance | |
CN107688850B (zh) | 一种深度神经网络压缩方法 | |
US10762426B2 (en) | Multi-iteration compression for deep neural networks | |
CN107688849B (zh) | 一种动态策略定点化训练方法及装置 | |
CN107679618B (zh) | 一种静态策略定点化训练方法及装置 | |
US20180046915A1 (en) | Compression of deep neural networks with proper use of mask | |
CN110084364B (zh) | 一种深度神经网络压缩方法和装置 | |
CN105488563A (zh) | 面向深度学习的稀疏自适应神经网络、算法及实现装置 | |
CN110929798A (zh) | 基于结构优化稀疏卷积神经网络的图像分类方法及介质 | |
CN113269312B (zh) | 一种联合量化与剪枝搜索的模型压缩方法及其系统 | |
CN114239861A (zh) | 基于多教师联合指导量化的模型压缩方法及系统 | |
US20220207374A1 (en) | Mixed-granularity-based joint sparse method for neural network | |
IL297848A (en) | Drift adjustment to neutralize changes in drift coefficients for analog boosters | |
US11710026B2 (en) | Optimization for artificial neural network model and neural processing unit | |
CN111967528A (zh) | 基于稀疏编码的深度学习网络结构搜索的图像识别方法 | |
CN116384471A (zh) | 模型剪枝方法、装置、计算机设备、存储介质和程序产品 | |
Zhou et al. | Deep adaptive network: An efficient deep neural network with sparse binary connections | |
CN114444654A (zh) | 一种面向nas的免训练神经网络性能评估方法、装置和设备 | |
CN116457794A (zh) | 用于神经网络模型的组平衡式稀疏激活特征图 | |
CN114519423A (zh) | 用于压缩神经网络的方法和装置 | |
CN112508194B (zh) | 模型压缩方法、系统和计算设备 | |
KR102647521B1 (ko) | Ann 모델과 npu의 최적화 | |
TWI813414B (zh) | 用於最佳化神經網路訓練之電腦實施之方法、系統及非暫時性電腦可讀取儲存媒體 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20180115 Address after: 100083 Beijing city Haidian District Wangzhuang Road No. 1 Building No. 4 hospital 8 floor No. 807 Applicant after: Beijing insight Technology Co., Ltd. Address before: 100084 Beijing city Haidian District Wangzhuang Road No. 1 Building No. 4 hospital 17 floor No. 1706 Applicant before: Beijing deep Intelligent Technology Co., Ltd. |
|
TA01 | Transfer of patent application right | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20180606 Address after: 100083, 17 floor, 4 Building 4, 1 Wang Zhuang Road, Haidian District, Beijing. Applicant after: Beijing deep Intelligent Technology Co., Ltd. Address before: 100083, 8 floor, 4 Building 4, 1 Wang Zhuang Road, Haidian District, Beijing. Applicant before: Beijing insight Technology Co., Ltd. |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20200903 Address after: Unit 01-19, 10 / F, 101, 6 / F, building 5, yard 5, Anding Road, Chaoyang District, Beijing 100029 Applicant after: Xilinx Electronic Technology (Beijing) Co., Ltd Address before: 100083, 17 floor, 4 Building 4, 1 Wang Zhuang Road, Haidian District, Beijing. Applicant before: BEIJING DEEPHI TECHNOLOGY Co.,Ltd. |
|
TA01 | Transfer of patent application right | ||
GR01 | Patent grant | ||
GR01 | Patent grant |