JP2020027399A5 - - Google Patents
Download PDFInfo
- Publication number
- JP2020027399A5 JP2020027399A5 JP2018151323A JP2018151323A JP2020027399A5 JP 2020027399 A5 JP2020027399 A5 JP 2020027399A5 JP 2018151323 A JP2018151323 A JP 2018151323A JP 2018151323 A JP2018151323 A JP 2018151323A JP 2020027399 A5 JP2020027399 A5 JP 2020027399A5
- Authority
- JP
- Japan
- Prior art keywords
- computer system
- pooling
- subsystems
- layer
- value
- 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.)
- Granted
Links
- 238000011176 pooling Methods 0.000 claims 24
- 238000000034 method Methods 0.000 claims 7
- 235000008694 Humulus lupulus Nutrition 0.000 claims 6
- 238000013527 convolutional neural network Methods 0.000 claims 5
- 238000013528 artificial neural network Methods 0.000 claims 1
- 238000004364 calculation method Methods 0.000 claims 1
- 239000006185 dispersion Substances 0.000 claims 1
- 230000006870 function Effects 0.000 claims 1
- 210000002569 neuron Anatomy 0.000 claims 1
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2018151323A JP7036689B2 (ja) | 2018-08-10 | 2018-08-10 | 計算機システム |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2018151323A JP7036689B2 (ja) | 2018-08-10 | 2018-08-10 | 計算機システム |
Publications (3)
| Publication Number | Publication Date |
|---|---|
| JP2020027399A JP2020027399A (ja) | 2020-02-20 |
| JP2020027399A5 true JP2020027399A5 (enExample) | 2021-04-22 |
| JP7036689B2 JP7036689B2 (ja) | 2022-03-15 |
Family
ID=69622172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2018151323A Active JP7036689B2 (ja) | 2018-08-10 | 2018-08-10 | 計算機システム |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP7036689B2 (enExample) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102192348B1 (ko) * | 2020-02-24 | 2020-12-17 | 한국과학기술원 | 불특정 다수의 주변 차량들에 대한 미래 경로 통합 예측을 위한 전자 장치 및 그의 동작 방법 |
| JP7412283B2 (ja) * | 2020-06-16 | 2024-01-12 | 株式会社Nttドコモ | 予測モデル生成システム及び予測システム |
| JP7659373B2 (ja) * | 2020-07-09 | 2025-04-09 | キヤノン株式会社 | 畳み込みニューラルネットワーク処理装置 |
| CN112560953B (zh) * | 2020-12-16 | 2023-08-15 | 中国平安财产保险股份有限公司 | 私家车非法营运的识别方法、系统、设备及存储介质 |
| CN115130642B (zh) * | 2021-03-26 | 2025-04-08 | 杭州海康威视数字技术股份有限公司 | 图卷积神经网络训练和图运算方法、装置、设备及系统 |
| CN115791640B (zh) * | 2023-02-06 | 2023-06-02 | 杭州华得森生物技术有限公司 | 基于分光光谱的肿瘤细胞检测设备及其方法 |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6897446B2 (ja) * | 2017-09-19 | 2021-06-30 | 富士通株式会社 | 探索方法、探索プログラムおよび探索装置 |
| US20190122111A1 (en) * | 2017-10-24 | 2019-04-25 | Nec Laboratories America, Inc. | Adaptive Convolutional Neural Knowledge Graph Learning System Leveraging Entity Descriptions |
-
2018
- 2018-08-10 JP JP2018151323A patent/JP7036689B2/ja active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP2020027399A5 (enExample) | ||
| US11645529B2 (en) | Sparsifying neural network models | |
| US11308398B2 (en) | Computation method | |
| EP3631625B1 (en) | ACCESSING DATA IN MULTIDIMENSIONAL TENSORS USING ADDERS | |
| EP3602280B1 (en) | Accessing prologue and epilogue data | |
| EP3407266B1 (en) | Artificial neural network calculating device and method for sparse connection | |
| WO2019091020A1 (zh) | 权重数据存储方法和基于该方法的神经网络处理器 | |
| US9785615B1 (en) | Memristive computation of a vector cross product | |
| US20160284400A1 (en) | Analog neuromorphic circuit implemented using resistive memories | |
| CN106991476A (zh) | 用于执行人工神经网络正向运算的装置和方法 | |
| US11868893B2 (en) | Efficient tile mapping for row-by-row convolutional neural network mapping for analog artificial intelligence network inference | |
| US11775832B2 (en) | Device and method for artificial neural network operation | |
| CN107818367A (zh) | 用于神经网络的处理系统和处理方法 | |
| WO2016107426A1 (en) | Systems and methods to adaptively select execution modes | |
| CN110929854B (zh) | 一种数据处理方法、装置及硬件加速器 | |
| WO2017148536A1 (en) | Electronic devices, artificial evolutionary neural networks, methods and computer programs for implementing evolutionary search and optimisation | |
| JP6926767B2 (ja) | 自己適応的なニューラル・ネットワーク | |
| CN111565065B (zh) | 一种无人机基站部署方法、装置及电子设备 | |
| CN112966729B (zh) | 一种数据处理方法、装置、计算机设备及存储介质 | |
| JP2019200657A (ja) | 演算装置及び演算装置の制御方法 | |
| US20220318634A1 (en) | Method and apparatus for retraining compressed model using variance equalization | |
| WO2023020419A1 (en) | System and method for bank-balanced sparse activation and joint-activation-weight-sparse training of neural networks | |
| WO2017198169A1 (en) | Reduction of parameters in fully connected layers of neural networks | |
| WO2017198168A2 (en) | Reduction of parameters in fully connected layers of neural networks by low rank factorizations | |
| CN116368493B (zh) | 用于具有随机架构的权重共享神经网络的方法和装置 |