CN108319988B - 一种用于手写汉字识别的深度神经网络的加速方法 - Google Patents
一种用于手写汉字识别的深度神经网络的加速方法 Download PDFInfo
- Publication number
- CN108319988B CN108319988B CN201710038008.0A CN201710038008A CN108319988B CN 108319988 B CN108319988 B CN 108319988B CN 201710038008 A CN201710038008 A CN 201710038008A CN 108319988 B CN108319988 B CN 108319988B
- Authority
- CN
- China
- Prior art keywords
- layer
- neural network
- convolutional
- deep
- 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
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 19
- 230000001133 acceleration Effects 0.000 title claims abstract description 17
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 39
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 29
- 238000010606 normalization Methods 0.000 claims abstract description 15
- 238000011176 pooling Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 9
- 238000011478 gradient descent method Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000013461 design Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 210000004205 output neuron Anatomy 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/24—Character recognition characterised by the processing or recognition method
- G06V30/242—Division of the character sequences into groups prior to recognition; Selection of dictionaries
- G06V30/244—Division of the character sequences into groups prior to recognition; Selection of dictionaries using graphical properties, e.g. alphabet type or font
- G06V30/2455—Discrimination between machine-print, hand-print and cursive writing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Character Discrimination (AREA)
Abstract
Description
Claims (4)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710038008.0A CN108319988B (zh) | 2017-01-18 | 2017-01-18 | 一种用于手写汉字识别的深度神经网络的加速方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710038008.0A CN108319988B (zh) | 2017-01-18 | 2017-01-18 | 一种用于手写汉字识别的深度神经网络的加速方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108319988A CN108319988A (zh) | 2018-07-24 |
CN108319988B true CN108319988B (zh) | 2021-12-24 |
Family
ID=62892936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710038008.0A Active CN108319988B (zh) | 2017-01-18 | 2017-01-18 | 一种用于手写汉字识别的深度神经网络的加速方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108319988B (zh) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109102070B (zh) * | 2018-08-22 | 2020-11-24 | 地平线(上海)人工智能技术有限公司 | 卷积神经网络数据的预处理方法和装置 |
CN111105007B (zh) * | 2018-10-26 | 2024-04-12 | 中国科学院半导体研究所 | 用于目标检测的深度卷积神经网络的压缩加速方法 |
WO2020087254A1 (zh) * | 2018-10-30 | 2020-05-07 | 深圳鲲云信息科技有限公司 | 卷积神经网络的优化方法及相关产品 |
CN109859167A (zh) * | 2018-12-28 | 2019-06-07 | 中国农业大学 | 黄瓜霜霉病严重度的评估方法及装置 |
CN110969165B (zh) * | 2019-11-28 | 2024-04-09 | 中国科学院半导体研究所 | 手写字符识别方法、装置、电子设备及存储介质 |
CN111914612B (zh) * | 2020-05-21 | 2024-03-01 | 淮阴工学院 | 一种基于改进的卷积神经网络的施工图图元自适应识别方法 |
CN112101343A (zh) * | 2020-08-17 | 2020-12-18 | 广东工业大学 | 一种车牌字符分割与识别方法 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105205448A (zh) * | 2015-08-11 | 2015-12-30 | 中国科学院自动化研究所 | 基于深度学习的文字识别模型训练方法和识别方法 |
CN106127297A (zh) * | 2016-06-02 | 2016-11-16 | 中国科学院自动化研究所 | 基于张量分解的深度卷积神经网络的加速与压缩方法 |
CN106326985A (zh) * | 2016-08-18 | 2017-01-11 | 北京旷视科技有限公司 | 神经网络训练方法和装置及数据处理方法和装置 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11423311B2 (en) * | 2015-06-04 | 2022-08-23 | Samsung Electronics Co., Ltd. | Automatic tuning of artificial neural networks |
-
2017
- 2017-01-18 CN CN201710038008.0A patent/CN108319988B/zh active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105205448A (zh) * | 2015-08-11 | 2015-12-30 | 中国科学院自动化研究所 | 基于深度学习的文字识别模型训练方法和识别方法 |
CN106127297A (zh) * | 2016-06-02 | 2016-11-16 | 中国科学院自动化研究所 | 基于张量分解的深度卷积神经网络的加速与压缩方法 |
CN106326985A (zh) * | 2016-08-18 | 2017-01-11 | 北京旷视科技有限公司 | 神经网络训练方法和装置及数据处理方法和装置 |
Also Published As
Publication number | Publication date |
---|---|
CN108319988A (zh) | 2018-07-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108319988B (zh) | 一种用于手写汉字识别的深度神经网络的加速方法 | |
CN106919942B (zh) | 用于手写汉字识别的深度卷积神经网络的加速压缩方法 | |
US10713533B2 (en) | Image processing method and apparatus, and computer-readable storage medium | |
Qiu et al. | FReLU: Flexible rectified linear units for improving convolutional neural networks | |
Yu et al. | On compressing deep models by low rank and sparse decomposition | |
US11403528B2 (en) | Self-tuning incremental model compression solution in deep neural network with guaranteed accuracy performance | |
CN110546656B (zh) | 前馈生成式神经网络 | |
US20220351043A1 (en) | Adaptive high-precision compression method and system based on convolutional neural network model | |
CN111126602A (zh) | 一种基于卷积核相似性剪枝的循环神经网络模型压缩方法 | |
CN109523014B (zh) | 基于生成式对抗网络模型的新闻评论自动生成方法及系统 | |
CN111814448B (zh) | 预训练语言模型量化方法和装置 | |
CN111104513B (zh) | 一种游戏平台用户问答业务的短文本分类方法 | |
CN111914994B (zh) | 多层感知机的生成方法、装置、电子设备及存储介质 | |
CN104915566A (zh) | 一种支持增量更新的深度计算模型设计方法 | |
Du et al. | Efficient network construction through structural plasticity | |
CN117744759A (zh) | 文本信息的识别方法、装置、存储介质及电子设备 | |
CN110895933B (zh) | 一种基于空时残差神经网络的远场语音识别方法 | |
CN111210815A (zh) | 一种用于语音命令词识别的深度神经网络构建方法和识别方法及装置 | |
Shrestha | Natural Gradient Methods: Perspectives, Efficient-Scalable Approximations, and Analysis | |
CN112101510A (zh) | 卷积神经网络推理加速方法、加速器、设备及存储介质 | |
CN116542315A (zh) | 一种基于张量分解的大规模神经网络参数压缩方法及系统 | |
Kim et al. | Fast convolution algorithm for convolutional neural networks | |
CN116245162A (zh) | 基于改进自适应遗传算法的神经网络剪枝方法及系统 | |
Jin et al. | Derivative-free optimization for low-rank adaptation in large language models | |
CN113033205B (zh) | 实体链接的方法、装置、设备以及存储介质 |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20240628 Address after: South China University of technology 381 Wushan Road Tianhe District Guangzhou City Guangdong Province Patentee after: SOUTH CHINA University OF TECHNOLOGY Country or region after: China Patentee after: FUJITSU RESEARCH AND DEVELOPMENT CENTER Co.,Ltd. Address before: 510640 South China University of technology, 381 Wushan Road, Tianhe District, Guangzhou City, Guangdong Province Patentee before: SOUTH CHINA University OF TECHNOLOGY Country or region before: China Patentee before: FUJITSU Ltd. Country or region before: Japan |
|
TR01 | Transfer of patent right |