DK3373209T3 - Dybdesammenkædning ved anvendelse af en matrixberegningsenhed - Google Patents
Dybdesammenkædning ved anvendelse af en matrixberegningsenhed Download PDFInfo
- Publication number
- DK3373209T3 DK3373209T3 DK18160441.4T DK18160441T DK3373209T3 DK 3373209 T3 DK3373209 T3 DK 3373209T3 DK 18160441 T DK18160441 T DK 18160441T DK 3373209 T3 DK3373209 T3 DK 3373209T3
- Authority
- DK
- Denmark
- Prior art keywords
- matrix calculator
- deep linking
- linking
- deep
- calculator
- Prior art date
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
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
-
- 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
-
- 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
- G06N3/06—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
- G06N3/065—Analogue 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Complex Calculations (AREA)
- Image Analysis (AREA)
- Design And Manufacture Of Integrated Circuits (AREA)
- Image Processing (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US15/452,624 US9691019B1 (en) | 2017-03-07 | 2017-03-07 | Depth concatenation using a matrix computation unit |
| US15/624,629 US10896367B2 (en) | 2017-03-07 | 2017-06-15 | Depth concatenation using a matrix computation unit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| DK3373209T3 true DK3373209T3 (da) | 2023-10-02 |
Family
ID=61873899
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| DK18160441.4T DK3373209T3 (da) | 2017-03-07 | 2018-03-07 | Dybdesammenkædning ved anvendelse af en matrixberegningsenhed |
Country Status (9)
| Country | Link |
|---|---|
| US (3) | US10896367B2 (da) |
| EP (2) | EP4235462A3 (da) |
| CN (1) | CN108572940B (da) |
| DE (2) | DE102018105198A1 (da) |
| DK (1) | DK3373209T3 (da) |
| FI (1) | FI3373209T3 (da) |
| GB (1) | GB2562826A (da) |
| TW (2) | TWI739225B (da) |
| WO (1) | WO2018165209A1 (da) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10896367B2 (en) | 2017-03-07 | 2021-01-19 | Google Llc | Depth concatenation using a matrix computation unit |
| US11144316B1 (en) | 2018-04-17 | 2021-10-12 | Ali Tasdighi Far | Current-mode mixed-signal SRAM based compute-in-memory for low power machine learning |
| US10867399B2 (en) | 2018-12-02 | 2020-12-15 | Himax Technologies Limited | Image processing circuit for convolutional neural network |
| TWI694413B (zh) * | 2018-12-12 | 2020-05-21 | 奇景光電股份有限公司 | 影像處理電路 |
| CN110033091B (zh) * | 2018-12-13 | 2020-09-01 | 阿里巴巴集团控股有限公司 | 一种基于模型进行预测的方法和装置 |
| JP6832329B2 (ja) * | 2018-12-18 | 2021-02-24 | 富士通株式会社 | データ構造 |
| US11928582B1 (en) * | 2018-12-31 | 2024-03-12 | Cadence Design Systems, Inc. | System, media, and method for deep learning |
| US11507642B2 (en) | 2019-05-02 | 2022-11-22 | Silicon Storage Technology, Inc. | Configurable input blocks and output blocks and physical layout for analog neural memory in deep learning artificial neural network |
| US11537939B2 (en) * | 2019-05-03 | 2022-12-27 | Google Llc | Reshape and broadcast optimizations to avoid unnecessary data movement |
| JP2020205003A (ja) * | 2019-06-19 | 2020-12-24 | キオクシア株式会社 | メモリシステム、メモリコントローラ、及び半導体記憶装置 |
| US10915298B1 (en) | 2019-10-08 | 2021-02-09 | Ali Tasdighi Far | Current mode multiply-accumulate for compute in memory binarized neural networks |
| US11615256B1 (en) | 2019-12-30 | 2023-03-28 | Ali Tasdighi Far | Hybrid accumulation method in multiply-accumulate for machine learning |
| US11610104B1 (en) | 2019-12-30 | 2023-03-21 | Ali Tasdighi Far | Asynchronous analog accelerator for fully connected artificial neural networks |
| US11314674B2 (en) * | 2020-02-14 | 2022-04-26 | Google Llc | Direct memory access architecture with multi-level multi-striding |
| US20220147808A1 (en) * | 2020-11-06 | 2022-05-12 | Micron Technology, Inc. | Compiler configurable to generate instructions executable by different deep learning accelerators from a description of an artificial neural network |
| US20220374689A1 (en) * | 2021-05-11 | 2022-11-24 | Xinlin LI | Methods and systems for computing an output of a neural network layer |
| US20220405598A1 (en) * | 2021-06-17 | 2022-12-22 | International Business Machines Corporation | Concatenated input/output tensors for use in recurrent neural networks |
| CN114547286A (zh) * | 2022-02-21 | 2022-05-27 | 京东科技控股股份有限公司 | 一种信息搜索方法、装置及电子设备 |
Family Cites Families (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5682441A (en) | 1995-11-08 | 1997-10-28 | Storm Technology, Inc. | Method and format for storing and selectively retrieving image data |
| TW305998B (en) | 1996-06-14 | 1997-05-21 | Ind Tech Res Inst | Weighted sum type of artificial neural network with reconfigurable structure and bit-serial I/O mode |
| US6240485B1 (en) * | 1998-05-11 | 2001-05-29 | Netlogic Microsystems, Inc. | Method and apparatus for implementing a learn instruction in a depth cascaded content addressable memory system |
| US6889293B1 (en) | 2000-06-09 | 2005-05-03 | Agere Systems Inc. | Directory-based prediction methods and apparatus for shared-memory multiprocessor systems |
| US9552047B2 (en) | 2001-03-05 | 2017-01-24 | Pact Xpp Technologies Ag | Multiprocessor having runtime adjustable clock and clock dependent power supply |
| US8269727B2 (en) | 2007-01-03 | 2012-09-18 | Apple Inc. | Irregular input identification |
| TW201034441A (en) | 2009-03-13 | 2010-09-16 | Chunghwa Picture Tubes Ltd | Method of establishing the depth of filed data for three-dimensional (3D) image and a system thereof |
| US9489176B2 (en) * | 2011-09-15 | 2016-11-08 | Exxonmobil Upstream Research Company | Optimized matrix and vector operations in instruction limited algorithms that perform EOS calculations |
| JP5780089B2 (ja) | 2011-09-28 | 2015-09-16 | 富士通株式会社 | 計算方法、計算プログラムおよび計算装置 |
| CN104040542B (zh) * | 2011-12-08 | 2017-10-10 | 甲骨文国际公司 | 用于在易失性存储器内保持关系型数据的列向量的技术 |
| US9292787B2 (en) * | 2012-08-29 | 2016-03-22 | Microsoft Technology Licensing, Llc | Computer-implemented deep tensor neural network |
| US20140181171A1 (en) * | 2012-12-24 | 2014-06-26 | Pavel Dourbal | Method and system for fast tensor-vector multiplication |
| CN103019656B (zh) * | 2012-12-04 | 2016-04-27 | 中国科学院半导体研究所 | 可动态重构的多级并行单指令多数据阵列处理系统 |
| US9384168B2 (en) | 2013-06-11 | 2016-07-05 | Analog Devices Global | Vector matrix product accelerator for microprocessor integration |
| ES2880316T3 (es) | 2014-08-29 | 2021-11-24 | Google Llc | Procesamiento de imágenes mediante redes neuronales profundas |
| US9524461B1 (en) | 2014-09-30 | 2016-12-20 | Steven T. Huynh | Conceptual computation system using a hierarchical network of modules |
| US20170061279A1 (en) | 2015-01-14 | 2017-03-02 | Intel Corporation | Updating an artificial neural network using flexible fixed point representation |
| US10192162B2 (en) | 2015-05-21 | 2019-01-29 | Google Llc | Vector computation unit in a neural network processor |
| US9747546B2 (en) | 2015-05-21 | 2017-08-29 | Google Inc. | Neural network processor |
| US10083395B2 (en) | 2015-05-21 | 2018-09-25 | Google Llc | Batch processing in a neural network processor |
| US9805303B2 (en) * | 2015-05-21 | 2017-10-31 | Google Inc. | Rotating data for neural network computations |
| US10049322B2 (en) | 2015-05-21 | 2018-08-14 | Google Llc | Prefetching weights for use in a neural network processor |
| US20160350652A1 (en) | 2015-05-29 | 2016-12-01 | North Carolina State University | Determining edit operations for normalizing electronic communications using a neural network |
| US10410119B2 (en) * | 2015-06-05 | 2019-09-10 | Deepmind Technologies Limited | Augmented recurrent neural network with external memory |
| US9614699B2 (en) | 2015-08-12 | 2017-04-04 | King Fahd University Of Petroleum And Minerals | Apparatuses and methodologies for decision feedback equalization using particle swarm optimization |
| US10282663B2 (en) * | 2015-08-15 | 2019-05-07 | Salesforce.Com, Inc. | Three-dimensional (3D) convolution with 3D batch normalization |
| CN106447035B (zh) * | 2015-10-08 | 2019-02-26 | 上海兆芯集成电路有限公司 | 具有可变率执行单元的处理器 |
| CN108351982B (zh) * | 2015-11-12 | 2022-07-08 | 谷歌有限责任公司 | 卷积门控递归神经网络 |
| US11170294B2 (en) * | 2016-01-07 | 2021-11-09 | Intel Corporation | Hardware accelerated machine learning |
| US9875104B2 (en) * | 2016-02-03 | 2018-01-23 | Google Llc | Accessing data in multi-dimensional tensors |
| CN105844279B (zh) | 2016-03-22 | 2019-04-23 | 西安电子科技大学 | 基于深度学习和sift特征的sar图像变化检测方法 |
| US10706348B2 (en) * | 2016-07-13 | 2020-07-07 | Google Llc | Superpixel methods for convolutional neural networks |
| US9691019B1 (en) | 2017-03-07 | 2017-06-27 | Google Inc. | Depth concatenation using a matrix computation unit |
| US10896367B2 (en) | 2017-03-07 | 2021-01-19 | Google Llc | Depth concatenation using a matrix computation unit |
-
2017
- 2017-06-15 US US15/624,629 patent/US10896367B2/en active Active
-
2018
- 2018-03-06 WO PCT/US2018/021221 patent/WO2018165209A1/en active Application Filing
- 2018-03-06 TW TW108143734A patent/TWI739225B/zh active
- 2018-03-06 TW TW107107502A patent/TWI686711B/zh active
- 2018-03-07 CN CN201810188352.2A patent/CN108572940B/zh active Active
- 2018-03-07 FI FIEP18160441.4T patent/FI3373209T3/fi active
- 2018-03-07 DE DE102018105198.0A patent/DE102018105198A1/de not_active Withdrawn
- 2018-03-07 EP EP23176027.3A patent/EP4235462A3/en active Pending
- 2018-03-07 DE DE202018101275.4U patent/DE202018101275U1/de active Active
- 2018-03-07 DK DK18160441.4T patent/DK3373209T3/da active
- 2018-03-07 EP EP18160441.4A patent/EP3373209B1/en active Active
- 2018-03-07 GB GB1803653.3A patent/GB2562826A/en not_active Withdrawn
-
2019
- 2019-08-05 US US16/531,774 patent/US10699182B2/en active Active
-
2021
- 2021-01-14 US US17/149,321 patent/US20210209444A1/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| CN108572940A (zh) | 2018-09-25 |
| GB201803653D0 (en) | 2018-04-25 |
| EP3373209A1 (en) | 2018-09-12 |
| TW202020856A (zh) | 2020-06-01 |
| TWI686711B (zh) | 2020-03-01 |
| DE202018101275U1 (de) | 2018-06-22 |
| TWI739225B (zh) | 2021-09-11 |
| TW201837737A (zh) | 2018-10-16 |
| US10896367B2 (en) | 2021-01-19 |
| EP3373209B1 (en) | 2023-07-05 |
| US20210209444A1 (en) | 2021-07-08 |
| CN108572940B (zh) | 2022-08-12 |
| DE102018105198A1 (de) | 2018-09-13 |
| US20190354834A1 (en) | 2019-11-21 |
| FI3373209T3 (fi) | 2023-09-15 |
| EP4235462A2 (en) | 2023-08-30 |
| US10699182B2 (en) | 2020-06-30 |
| EP4235462A3 (en) | 2023-09-06 |
| US20180260683A1 (en) | 2018-09-13 |
| GB2562826A (en) | 2018-11-28 |
| WO2018165209A1 (en) | 2018-09-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| DK3373209T3 (da) | Dybdesammenkædning ved anvendelse af en matrixberegningsenhed | |
| DK3602409T3 (da) | Udvælgelse af handlinger ved hjælp af multimodale inputs | |
| DK3180426T3 (da) | Genomredigering ved anvendelse af cas9-nickaser | |
| DK3079106T3 (da) | UDVÆLGELSE AF FORSTÆRKNINGSLÆRINGSHANDLINGER VED HJÆLP AF MÅL og OBSERVATIONER | |
| FR3033439B1 (fr) | Resource management | |
| DK3523661T3 (da) | Vindmåling ved hjælp af en multikopter | |
| DK3177126T3 (da) | Køling af et datacenter | |
| DK3262513T3 (da) | Lagring af data | |
| DK3164367T3 (da) | Udglatning af en coating | |
| DK3188963T3 (da) | Forbedring af en skrue | |
| DK3271477T3 (da) | Dråbebaseret udvælgelse ved injektion | |
| FR3040422B1 (fr) | Carottier a piston statique | |
| DK3319277T3 (da) | Tilvejebringelse af adgang til et netværk | |
| FR3046256B1 (fr) | Zoom plenoptique a portee optimisee | |
| FR3046841B1 (fr) | Couplemetre a torsion | |
| FR3043190B1 (fr) | Refouloir a obus | |
| FR3020870B1 (fr) | Carabine a verrou ambidextre | |
| DK3241960T3 (da) | En lås | |
| BR212017023420U2 (pt) | um cilíndro | |
| DK3377603T3 (da) | Fremstilling af en stabil øl | |
| FR3051235B1 (fr) | Palier a roulement | |
| FR3045747B1 (fr) | Palier a roulement | |
| FR3042005B1 (fr) | Palier a roulement | |
| DK3109461T3 (da) | Drift af en vindmølle | |
| FR3021937B1 (fr) | Servofrein a depression |