CN108009625B - 人工神经网络定点化后的微调方法和装置 - Google Patents
人工神经网络定点化后的微调方法和装置 Download PDFInfo
- Publication number
- CN108009625B CN108009625B CN201611033156.5A CN201611033156A CN108009625B CN 108009625 B CN108009625 B CN 108009625B CN 201611033156 A CN201611033156 A CN 201611033156A CN 108009625 B CN108009625 B CN 108009625B
- Authority
- CN
- China
- Prior art keywords
- layer
- ann
- point
- tuning
- network
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (17)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611033156.5A CN108009625B (zh) | 2016-11-01 | 2016-11-01 | 人工神经网络定点化后的微调方法和装置 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611033156.5A CN108009625B (zh) | 2016-11-01 | 2016-11-01 | 人工神经网络定点化后的微调方法和装置 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108009625A CN108009625A (zh) | 2018-05-08 |
CN108009625B true CN108009625B (zh) | 2020-11-06 |
Family
ID=62048541
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611033156.5A Active CN108009625B (zh) | 2016-11-01 | 2016-11-01 | 人工神经网络定点化后的微调方法和装置 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108009625B (zh) |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110555450B (zh) * | 2018-05-31 | 2022-06-28 | 赛灵思电子科技(北京)有限公司 | 人脸识别神经网络调整方法和装置 |
CN110555508B (zh) * | 2018-05-31 | 2022-07-12 | 赛灵思电子科技(北京)有限公司 | 人工神经网络调整方法和装置 |
CN110598723B (zh) * | 2018-06-13 | 2023-12-12 | 赛灵思电子科技(北京)有限公司 | 人工神经网络调整方法和装置 |
CN110929858A (zh) * | 2018-09-20 | 2020-03-27 | 耐能智慧股份有限公司 | 算数框架系统及操作浮点至定点算数框架的方法 |
US11663464B2 (en) * | 2018-09-20 | 2023-05-30 | Kneron (Taiwan) Co., Ltd. | Deep neural network with low-precision dynamic fixed-point in reconfigurable hardware design |
WO2020097837A1 (en) | 2018-11-15 | 2020-05-22 | Lingdong Technology (Beijing) Co.Ltd | System and method for real-time supervised machine learning in on-site environment |
CN109359727B (zh) * | 2018-12-07 | 2022-01-11 | 北京字节跳动网络技术有限公司 | 神经网络的结构确定方法、装置、设备及可读介质 |
CN111353517B (zh) * | 2018-12-24 | 2023-09-26 | 杭州海康威视数字技术股份有限公司 | 一种车牌识别方法、装置及电子设备 |
CN109711358B (zh) * | 2018-12-28 | 2020-09-04 | 北京远鉴信息技术有限公司 | 神经网络训练方法、人脸识别方法及系统和存储介质 |
CN111695671B (zh) * | 2019-03-12 | 2023-08-08 | 北京地平线机器人技术研发有限公司 | 训练神经网络的方法及装置、电子设备 |
CN110070867B (zh) * | 2019-04-26 | 2022-03-11 | 珠海普林芯驰科技有限公司 | 语音指令识别方法、计算机装置及计算机可读存储介质 |
CN110298438B (zh) * | 2019-07-05 | 2024-04-26 | 北京中星微电子有限公司 | 神经网络模型的调整方法和调整装置 |
WO2021016932A1 (zh) * | 2019-07-31 | 2021-02-04 | 深圳市大疆创新科技有限公司 | 数据处理方法、装置及计算机可读存储介质 |
CN110472700B (zh) * | 2019-10-14 | 2020-06-16 | 深兰人工智能芯片研究院(江苏)有限公司 | 一种基于卷积神经网络的参数填充方法与装置 |
US11797850B2 (en) | 2020-07-09 | 2023-10-24 | Lynxi Technologies Co., Ltd. | Weight precision configuration method and apparatus, computer device and storage medium |
CN111831356B (zh) * | 2020-07-09 | 2023-04-07 | 北京灵汐科技有限公司 | 权重精度配置方法、装置、设备及存储介质 |
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 |
CN112561933A (zh) * | 2020-12-15 | 2021-03-26 | 深兰人工智能(深圳)有限公司 | 图像分割方法及装置 |
CN112541438A (zh) * | 2020-12-15 | 2021-03-23 | 深兰人工智能(深圳)有限公司 | 文本识别方法及装置 |
CN113026457B (zh) * | 2021-03-23 | 2022-08-12 | 广联达科技股份有限公司 | 道路施工的标段确定方法及确定装置 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101847087B (zh) * | 2010-04-28 | 2012-03-28 | 中国科学院自动化研究所 | 一种支持定浮点可重构的横向求和网络结构 |
US8743493B1 (en) * | 2013-01-16 | 2014-06-03 | Lsi Corporation | Fixed-point processing using quantization levels based on floating-point processing |
CN104346440B (zh) * | 2014-10-10 | 2017-06-23 | 浙江大学 | 一种基于神经网络的跨媒体哈希索引方法 |
US9563825B2 (en) * | 2014-11-20 | 2017-02-07 | Adobe Systems Incorporated | Convolutional neural network using a binarized convolution layer |
CN105760933A (zh) * | 2016-02-18 | 2016-07-13 | 清华大学 | 卷积神经网络的逐层变精度定点化方法及装置 |
-
2016
- 2016-11-01 CN CN201611033156.5A patent/CN108009625B/zh active Active
Also Published As
Publication number | Publication date |
---|---|
CN108009625A (zh) | 2018-05-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108009625B (zh) | 人工神经网络定点化后的微调方法和装置 | |
CN107688855B (zh) | 针对于复杂神经网络的分层量化方法与装置 | |
US11847561B2 (en) | Adaptive artificial neural network selection techniques | |
JP7218805B2 (ja) | ソフトクロスエントロピー損失を用いたセマンティックセグメンテーション | |
US10643124B2 (en) | Method and device for quantizing complex artificial neural network | |
RU2747445C1 (ru) | Устройство обработки данных, способ обработки данных и носитель данных | |
US20180197084A1 (en) | Convolutional neural network system having binary parameter and operation method thereof | |
CN110097084B (zh) | 通过投射特征训练多任务学生网络的知识融合方法 | |
CN113469283A (zh) | 一种图像分类方法、图像分类模型的训练方法及设备 | |
Faraone et al. | Customizing low-precision deep neural networks for FPGAs | |
CN111598238A (zh) | 深度学习模型的压缩方法及装置 | |
US20220092391A1 (en) | System and method of using neuroevolution-enhanced multi-objective optimization for mixed-precision quantization of deep neural networks | |
Lahoud et al. | Self-binarizing networks | |
CN115546601A (zh) | 一种多目标识别模型及其构建方法、装置及应用 | |
US9443168B1 (en) | Object detection approach using an ensemble strong classifier | |
US11500767B2 (en) | Method and device for determining a global memory size of a global memory size for a neural network | |
KR102374525B1 (ko) | 키워드 스폿팅 장치, 방법 및 컴퓨터 판독 가능한 기록매체 | |
CN116257751A (zh) | 基于在线协作与特征融合的蒸馏方法与装置 | |
CN113743593A (zh) | 神经网络量化方法、系统、存储介质及终端 | |
Chu et al. | Mixed-precision quantized neural network with progressively decreasing bitwidth for image classification and object detection | |
CN112149805A (zh) | 基于框架搜索的深度神经网络的加速与压缩方法及系统 | |
Kollek et al. | Improving neural network architecture compression by multi-grain pruning | |
US20240185033A1 (en) | Method for training graph neural network, apparatus for processing pre-trained graph neural network, and storage medium storing instructions to perform method for training graph neural network | |
US20230409869A1 (en) | Process for transforming a trained artificial neuron network | |
CN117010452A (zh) | 神经网络搜索方法、装置、设备和存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20180606 Address after: 100083, 17 floor, four building four, 1 Wang Zhuang Road, Haidian District, Beijing. Applicant after: Beijing deep Intelligent Technology Co., Ltd. Address before: 100083, 8 floor, 807 building, four building, 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: 20190926 Address after: 2100 San Jose Rojack Avenue, California, USA Applicant after: XILINX INC Address before: 100083, 17 floor, four building four, 1 Wang Zhuang Road, Haidian District, Beijing. Applicant before: Beijing Shenjian Intelligent Technology Co., Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |