KR20230073757A - 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 - Google Patents
심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 Download PDFInfo
- Publication number
- KR20230073757A KR20230073757A KR1020210160472A KR20210160472A KR20230073757A KR 20230073757 A KR20230073757 A KR 20230073757A KR 1020210160472 A KR1020210160472 A KR 1020210160472A KR 20210160472 A KR20210160472 A KR 20210160472A KR 20230073757 A KR20230073757 A KR 20230073757A
- Authority
- KR
- South Korea
- Prior art keywords
- pruning
- trunk
- layer
- kernels
- kernel
- Prior art date
Links
- 238000013138 pruning Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 62
- 238000013528 artificial neural network Methods 0.000 title description 22
- 238000012549 training Methods 0.000 title description 8
- 238000013135 deep learning Methods 0.000 claims abstract description 9
- 238000010606 normalization Methods 0.000 claims abstract description 9
- 230000008569 process Effects 0.000 description 18
- 230000006870 function Effects 0.000 description 16
- 230000004913 activation Effects 0.000 description 15
- 230000000694 effects Effects 0.000 description 8
- 230000009467 reduction Effects 0.000 description 8
- 230000008901 benefit Effects 0.000 description 7
- 238000013527 convolutional neural network Methods 0.000 description 7
- 230000015556 catabolic process Effects 0.000 description 5
- 238000006731 degradation reaction Methods 0.000 description 5
- 230000006835 compression Effects 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 238000007796 conventional method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual 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
- G06N3/08—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
- G06N3/08—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
- G06N3/088—Non-supervised learning, e.g. competitive learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Filters That Use Time-Delay Elements (AREA)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210160472A KR20230073757A (ko) | 2021-11-19 | 2021-11-19 | 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 |
PCT/KR2021/017227 WO2023090499A1 (fr) | 2021-11-19 | 2021-11-23 | Procédé d'élagage de filtre basé sur l'apprentissage de la rareté pour réseaux neuronaux profonds |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020210160472A KR20230073757A (ko) | 2021-11-19 | 2021-11-19 | 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 |
Publications (1)
Publication Number | Publication Date |
---|---|
KR20230073757A true KR20230073757A (ko) | 2023-05-26 |
Family
ID=86397142
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020210160472A KR20230073757A (ko) | 2021-11-19 | 2021-11-19 | 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR20230073757A (fr) |
WO (1) | WO2023090499A1 (fr) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10482337B2 (en) * | 2017-09-29 | 2019-11-19 | Infineon Technologies Ag | Accelerating convolutional neural network computation throughput |
KR102225308B1 (ko) * | 2017-11-28 | 2021-03-09 | 주식회사 날비컴퍼니 | 컨볼루션 신경망 내 필터 프루닝 장치 및 방법 |
KR102165273B1 (ko) * | 2019-04-02 | 2020-10-13 | 국방과학연구소 | 소형 뉴럴 네트워크의 채널 프루닝(pruning) 방법 및 시스템 |
KR20210012882A (ko) * | 2019-07-25 | 2021-02-03 | 삼성전자주식회사 | 컨볼루션 뉴럴 네트워크의 성능 향상을 위한 방법 및 시스템 |
-
2021
- 2021-11-19 KR KR1020210160472A patent/KR20230073757A/ko unknown
- 2021-11-23 WO PCT/KR2021/017227 patent/WO2023090499A1/fr unknown
Also Published As
Publication number | Publication date |
---|---|
WO2023090499A1 (fr) | 2023-05-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11741342B2 (en) | Resource-efficient neural architects | |
CN109726045B (zh) | 用于块稀疏递归神经网络的系统和方法 | |
Tung et al. | Deep neural network compression by in-parallel pruning-quantization | |
CN112508169A (zh) | 知识蒸馏方法和系统 | |
EP4372616A1 (fr) | Système et procédé pour réseaux d'autoroute récurrentes normalisés par lots | |
CN111709493B (zh) | 对象分类方法、训练方法、装置、设备及存储介质 | |
US11544526B2 (en) | Computing device and method | |
CN110782008A (zh) | 深度学习模型的训练方法、预测方法和装置 | |
US11222054B2 (en) | Low-complexity methods for assessing distances between pairs of documents | |
Pietron et al. | Retrain or not retrain?-efficient pruning methods of deep cnn networks | |
CN114049527B (zh) | 基于在线协作与融合的自我知识蒸馏方法与系统 | |
CN114118406A (zh) | 一种卷积神经网络的量化压缩方法 | |
CN113792621A (zh) | 一种基于fpga的目标检测加速器设计方法 | |
He et al. | Learned transferable architectures can surpass hand-designed architectures for large scale speech recognition | |
CN112200310B (zh) | 智能处理器、数据处理方法及存储介质 | |
CN113870863A (zh) | 声纹识别方法及装置、存储介质及电子设备 | |
Zhou et al. | AdaptCL: Efficient collaborative learning with dynamic and adaptive pruning | |
US20220027719A1 (en) | Compressing tokens based on positions for transformer models | |
Cowen et al. | Lsalsa: accelerated source separation via learned sparse coding | |
CN112487933A (zh) | 一种基于自动化深度学习的雷达波形识别方法及系统 | |
KR20230073757A (ko) | 심층신경망을 위한 희소성 학습 기반 필터 프루닝 기법 | |
CN112418388A (zh) | 一种实现深度卷积神经网络处理的方法及装置 | |
Liu et al. | Flexi-compression: a flexible model compression method for autonomous driving | |
CN116957006A (zh) | 预测模型的训练方法、装置、设备、介质及程序产品 | |
US11954448B2 (en) | Determining position values for transformer models |