期刊文献+
共找到294篇文章
< 1 2 15 >
每页显示 20 50 100
Stability of Iterative Learning Control with Data Dropouts via Asynchronous Dynamical System 被引量:18
1
作者 Xu-Hui Bu Zhong-Sheng Hou 《International Journal of Automation and computing》 EI 2011年第1期29-36,共8页
In this paper, the stability of iterative learning control with data dropouts is discussed. By the super vector formulation, an iterative learning control (ILC) system with data dropouts can be modeled as an asynchr... In this paper, the stability of iterative learning control with data dropouts is discussed. By the super vector formulation, an iterative learning control (ILC) system with data dropouts can be modeled as an asynchronous dynamical system with rate constraints on events in the iteration domain. The stability condition is provided in the form of linear matrix inequalities (LMIS) depending on the stability of asynchronous dynamical systems. The analysis is supported by simulations. 展开更多
关键词 Iterative learning control (ILC) networked control systems (NCSs) data dropouts asynchronous dynamical system robustness.
在线阅读 下载PDF
On the loss mechanisms of radiation belt electron dropouts during the 12 September 2014 geomagnetic storm 被引量:9
2
作者 Xin Ma Zheng Xiang +8 位作者 BinBin Ni Song Fu Xing Cao Man Hua DeYu Guo YingJie Guo XuDong Gu ZeYuan Liu Qi Zhu 《Earth and Planetary Physics》 CSCD 2020年第6期598-610,共13页
Radiation belt electron dropouts indicate electron flux decay to the background level during geomagnetic storms,which is commonly attributed to the effects of wave-induced pitch angle scattering and magnetopause shado... Radiation belt electron dropouts indicate electron flux decay to the background level during geomagnetic storms,which is commonly attributed to the effects of wave-induced pitch angle scattering and magnetopause shadowing.To investigate the loss mechanisms of radiation belt electron dropouts triggered by a solar wind dynamic pressure pulse event on 12 September 2014,we comprehensively analyzed the particle and wave measurements from Van Allen Probes.The dropout event was divided into three periods:before the storm,the initial phase of the storm,and the main phase of the storm.The electron pitch angle distributions(PADs)and electron flux dropouts during the initial and main phases of this storm were investigated,and the evolution of the radial profile of electron phase space density(PSD)and the(μ,K)dependence of electron PSD dropouts(whereμ,K,and L^*are the three adiabatic invariants)were analyzed.The energy-independent decay of electrons at L>4.5 was accompanied by butterfly PADs,suggesting that the magnetopause shadowing process may be the major loss mechanism during the initial phase of the storm at L>4.5.The features of electron dropouts and 90°-peaked PADs were observed only for>1 MeV electrons at L<4,indicating that the wave-induced scattering effect may dominate the electron loss processes at the lower L-shell during the main phase of the storm.Evaluations of the(μ,K)dependence of electron PSD drops and calculations of the minimum electron resonant energies of H+-band electromagnetic ion cyclotron(EMIC)waves support the scenario that the observed PSD drop peaks around L^*=3.9 may be caused mainly by the scattering of EMIC waves,whereas the drop peaks around L^*=4.6 may result from a combination of EMIC wave scattering and outward radial diffusion. 展开更多
关键词 radiation belt electron flux dropouts geomagnetic storm electron phase space density magnetopause shadowing wave-particle interactions
在线阅读 下载PDF
Optimal full-order filtering for discrete-time systems with random measurement delays and multiple packet dropouts 被引量:5
3
作者 Shuli SUN Lihua XIE Wendong XIAO 《控制理论与应用(英文版)》 EI 2010年第1期105-110,共6页
This paper is concerned with the estimation problem for discrete-time stochastic linear systems with possible single unit delay and multiple packet dropouts. Based on a proposed uncertain model in data transmission, a... This paper is concerned with the estimation problem for discrete-time stochastic linear systems with possible single unit delay and multiple packet dropouts. Based on a proposed uncertain model in data transmission, an optimal full-order filter for the state of the system is presented, which is shown to be of the form of employing the received outputs at the current and last time instants. The solution to the optimal filter is given in terms of a Riccati difference equation governed by two binary random variables. The optimal filter is reduced to the standard Kalman filter when there are no random delays and packet dropouts. The steady-state filter is also investigated. A sufficient condition for the existence of the steady-state filter is given. The asymptotic stability of the optimal filter is analyzed. 展开更多
关键词 Full-order filter Random delay Packet dropouts Riccati difference equation
在线阅读 下载PDF
Fault detection for networked systems subject to access constraints and packet dropouts 被引量:3
4
作者 Xiongbo Wan Huajing Fang Sheng Fu 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2011年第1期127-134,共8页
This paper addresses the problem of fault detection(FD) for networked systems with access constraints and packet dropouts.Two independent Markov chains are used to describe the sequences of channels which are availa... This paper addresses the problem of fault detection(FD) for networked systems with access constraints and packet dropouts.Two independent Markov chains are used to describe the sequences of channels which are available for communication at an instant and the packet dropout process,respectively.Performance indexes H∞ and H_ are introduced to describe the robustness of residual against external disturbances and sensitivity of residual to faults,respectively.By using a mode-dependent fault detection filter(FDF) as residual generator,the addressed FD problem is converted into an auxiliary filter design problem with the above index constraints.A sufficient condition for the existence of the FDF is derived in terms of certain linear matrix inequalities(LMIs).When these LMIs are feasible,the explicit expression of the desired FDF can also be characterized.A numerical example is exploited to show the usefulness of the proposed results. 展开更多
关键词 fault detection(FD) networked control system(NCS) access constraints packet dropouts linear matrix inequality(LMI).
在线阅读 下载PDF
Observer-based H-infinity control in multiple channel networked control systems with random packet dropouts 被引量:1
5
作者 Weiwei CHE Jianliang WANG Guanghong YANG 《控制理论与应用(英文版)》 EI 2010年第3期359-367,共9页
This paper investigates the observer-based H-infinity control problem for networked control systems (NCSs) with random packet dropouts. A general packet dropout model with multiple independent stochastic variables i... This paper investigates the observer-based H-infinity control problem for networked control systems (NCSs) with random packet dropouts. A general packet dropout model with multiple independent stochastic variables in the multiple channels case is adopted to describe the data missing in the limited communication channels. With the consideration of the sensor-to-controller and controller-to-actuator packet dropouts at the same time, a new method is pro- posed based on a separation lemma to design an observer-based H-infinity controller, which exponentially stabilizes the closed-loop system in the sense of mean square and also achieves a prescribed H-infinity disturbance attenuation level. A numerical example is given to illustrate the effectiveness of the proposed control method. 展开更多
关键词 Networked control system (NCS) H-infinity control Separation lemma Random packet dropouts LMI
在线阅读 下载PDF
Chinese Students in Japan Help School Dropouts at Home
6
作者 CHUN YAN 《The Journal of Human Rights》 2006年第2期15-16,共2页
In 2004, Wang Chengyan, a 13-year-old Mongolian girl in the Tumote Left Banner of Inner Mongolia, took up her schoolbag again and marched into the classroom of six grade of a local primary school. With her face shinin... In 2004, Wang Chengyan, a 13-year-old Mongolian girl in the Tumote Left Banner of Inner Mongolia, took up her schoolbag again and marched into the classroom of six grade of a local primary school. With her face shining with brilliance, she told her friends: "It is brothers and sisters studying in Japan who have paid my way to school." 展开更多
关键词 HELP SCHOOL Chinese Students in Japan Help School dropouts at Home
原文传递
Robust sliding mode control for uncertain networked control system with two-channel packet dropouts 被引量:5
7
作者 ZHANG Yu REN Li-tong +2 位作者 XIE Shou-sheng ZHANG Le-di ZHOU Bin 《Journal of Central South University》 SCIE EI CAS CSCD 2019年第4期881-892,共12页
A robust sliding mode control algorithm is developed for a class of networked control system with packet dropouts in both sensor-controller channel and controller-actuator channel,and at the same time mismatched param... A robust sliding mode control algorithm is developed for a class of networked control system with packet dropouts in both sensor-controller channel and controller-actuator channel,and at the same time mismatched parametric uncertainty and external disturbance are also taken into consideration.A two-level Bernoulli process has been used to describe the packet dropouts existing in both channels.A novel integral sliding surface is proposed,based on which the H∞performance of system sliding mode motion is analyzed.Then the sufficient condition for system stability and robustness is derived in the form of linear matrix inequality(LMI).A sliding mode controller is designed which can guarantee a relatively ideal system dynamic performance and has certain robustness against unknown parameter perturbations and external disturbances.The results from numerical simulations are presented to corroborate the validity of the proposed controller. 展开更多
关键词 networked control system sliding mode control packet dropout UNCERTAINTY
在线阅读 下载PDF
Impulsive controller design for nonlinear networked control systems with time delay and packet dropouts 被引量:2
8
作者 Xianlin Zhao Shumin Fei Jinxing Lin 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2012年第3期414-418,共5页
The globally exponential stability of nonlinear impul- sive networked control systems (NINCS) with time delay and packet dropouts is investigated. By applying Lyapunov function theory, sufficient conditions on the g... The globally exponential stability of nonlinear impul- sive networked control systems (NINCS) with time delay and packet dropouts is investigated. By applying Lyapunov function theory, sufficient conditions on the global exponential stability are derived by introducing a comparison system and estimating the corresponding Cauchy matrix. An impulsive controller is explicitly designed to achieve exponential stability and ensure state con- verge with a given decay rate for the system. The Lorenz oscillator system is presented as a numerical example to illustrate the theo- retical results and effectiveness of the proposed controller design procedure. 展开更多
关键词 nonlinear impulsive networked control system (NINCS) exponential stability packet dropout.
在线阅读 下载PDF
Enabling Proactive Management of School Dropouts Using Neural Network
9
作者 Khamisi Kalegele 《Journal of Software Engineering and Applications》 2020年第10期245-257,共13页
<div style="text-align:justify;"> <span style="font-family:Verdana;">The growing need to use Artificial Intelligence (AI) technologies in addressing challenges in education sectors of d... <div style="text-align:justify;"> <span style="font-family:Verdana;">The growing need to use Artificial Intelligence (AI) technologies in addressing challenges in education sectors of developing countries is undermined by low awareness, limited skill and poor data quality. One particular persisting challenge, which can be addressed by AI, is school dropouts whereby hundreds of thousands of children drop annually in Africa. This article presents a data-driven approach to proactively predict likelihood of dropping from schools and enable effective management of dropouts. The approach is guided by a carefully crafted conceptual framework and new concepts of average absenteeism, current cumulative absenteeism and dropout risk appetite. In this study, a typical scenario of missing quality data is considered and for which synthetic data is generated to enable development of a functioning prediction model using neural network. The results show that, using the proposed approach, the levels of risk of dropping out of schools can be practically determined using data that is largely available in schools. Potentially, the study will inspire further research, encourage deployment of the technologies in real life, and inform processes of formulating or improving policies.</span> </div> 展开更多
关键词 DROPOUT Machine Learning School Management
在线阅读 下载PDF
基于深度学习网络的OFDM信号识别方法研究
10
作者 熊刚 刘涛 耿亮 《舰船电子对抗》 2025年第3期93-97,共5页
由于当今通信网络技术的蓬勃发展,电磁空间环境也更加错综复杂。针对复杂电磁环境中的正交频分复用(OFDM)信号识别问题,提出了一种基于深度学习网络——卷积神经网络(CNN)的识别方法,通过对卷积网络结构以及分类模型参数设计的优化,使... 由于当今通信网络技术的蓬勃发展,电磁空间环境也更加错综复杂。针对复杂电磁环境中的正交频分复用(OFDM)信号识别问题,提出了一种基于深度学习网络——卷积神经网络(CNN)的识别方法,通过对卷积网络结构以及分类模型参数设计的优化,使得算法具有良好的抗噪性与识别准确率。仿真结果表明新方法的识别性能较佳,在低信噪比情况下比过去一些传统的算法具有更好的识别性能,为OFDM信号的识别提供了参考。 展开更多
关键词 正交频分复用信号 卷积神经网络 调制识别 Dropout策略
在线阅读 下载PDF
一种特征感知与引导的无监督立体匹配算法
11
作者 魏东 郑博闻 王思雨 《计算机技术与发展》 2025年第6期158-165,共8页
针对立体匹配算法在处理物体边缘、视差不连续等细节时面临的挑战,以及有监督算法对数据标注的高度依赖性,提出了一种特征感知与引导的无监督立体匹配算法。该算法在生成器的编码器部分嵌入特征感知模块。该模块结合残差网络的稳健性,... 针对立体匹配算法在处理物体边缘、视差不连续等细节时面临的挑战,以及有监督算法对数据标注的高度依赖性,提出了一种特征感知与引导的无监督立体匹配算法。该算法在生成器的编码器部分嵌入特征感知模块。该模块结合残差网络的稳健性,确保了特征提取的稳定性,还结合空洞金字塔卷积网络的广感受野特性,有效地扩大了特征捕捉的范围,此外,还辅以软池化技术,以增强特征的层次性和丰富性,使算法能够更好地应对图像中的细节变化。为进一步提升特征的表征能力,引入了特征引导模块,通过结合通道注意力和空间注意力机制,动态调整不同通道和空间位置的权重来有效聚焦于关键特征区域。此外,在判别器中加入Dropout层,以随机丢弃部分神经元连接的方式促使模型训练更加稳定,避免过拟合情况发生。为了验证算法的有效性,实验采用了KITTI 2015数据集进行评估。结果表明,与其他经典算法相比,该算法在细节及区域的效果、精度方面均有提升。 展开更多
关键词 立体匹配 无监督 特征感知 特征引导 DROPOUT
在线阅读 下载PDF
基于ABC-LSTM模型的锂离子电池剩余使用寿命预测 被引量:2
12
作者 刘勇 于怀汶 +3 位作者 刘大鹏 穆勇 王瀛洲 张秀宇 《储能科学与技术》 北大核心 2025年第1期331-345,共15页
为了保证储能系统的安全稳定运行,准确预测锂离子电池的剩余使用寿命(remaining useful life,RUL)至关重要。本工作提出了一种基于人工蜂群算法(artificial bee colony,ABC)和结合dropout技术的长短期记忆网络(long short-term memory,L... 为了保证储能系统的安全稳定运行,准确预测锂离子电池的剩余使用寿命(remaining useful life,RUL)至关重要。本工作提出了一种基于人工蜂群算法(artificial bee colony,ABC)和结合dropout技术的长短期记忆网络(long short-term memory,LSTM)相结合的综合预测模型,可有效提高锂离子电池RUL预测的准确性。首先,利用dropout正则化方法有效减轻过拟合现象的优势,提高预测模型的泛化能力。其次,引入针对容量回升及数据噪声问题的激活层网络结构,显著提升模型对复杂非线性数据的处理能力。然后,结合ABC算法优化LSTM综合预测模型的超参数,避免模型陷入局部最优解,提高RUL预测精度。最后,通过NASA研究中心及CALCE的公开数据集验证所提模型的预测准确性和鲁棒性。本工作对基于40%和60%训练数据的不同算法预测性能进行实验分析验证,并与麻雀优化算法、座头鲸优化算法等群体优化算法进行比较。实验结果表明,所提出的ABC-LSTM综合预测模型可以更加准确地捕获锂离子电池容量退化的全局趋势及局部特征,其中60%比例的RUL预测结果的均方根误差平均保持在1.02%以内,平均绝对误差平均保持在0.86%以内,拟合系数高达97%以上。 展开更多
关键词 锂离子电池 剩余使用寿命预测 长短期记忆网络 人工蜂群算法 dropout技术
在线阅读 下载PDF
带有Dropout结构的贝叶斯近似宽度学习系统
13
作者 陈滔 王立杰 +2 位作者 刘洋 徐丽莉 于海生 《控制理论与应用》 北大核心 2025年第8期1632-1640,共9页
宽度学习系统(BLS)及其改进算法均普遍存在一个问题,即随着实际场景中数据复杂性的逐步增强,网络结构变得极其复杂,进一步导致计算资源的消耗也大幅度增加.针对此问题,本文提出了一种带有Dropout算法的贝叶斯近似宽度学习系统(Dropout-B... 宽度学习系统(BLS)及其改进算法均普遍存在一个问题,即随着实际场景中数据复杂性的逐步增强,网络结构变得极其复杂,进一步导致计算资源的消耗也大幅度增加.针对此问题,本文提出了一种带有Dropout算法的贝叶斯近似宽度学习系统(Dropout-BABLS).首先,利用Dropout算法对宽度学习系统的隐藏层节点随机进行丢弃.其次,通过结合高斯回归过程和贝叶斯理论近似Dropout对输出结果的损失函数以确定Dropout-BABLS的目标函数,进一步采用增广拉格朗日乘子法对目标函数的输出权重进行优化求解.最后,通过UCI机器学习知识库的10组回归数据集和自建的6组时间序列数据集对算法进行分析评估.结果表明,本文所提出的Dropout-BABLS算法能保证相应的输出精度,并减少25%~50%的训练时间. 展开更多
关键词 宽度学习系统 DROPOUT 高斯过程 贝叶斯近似 拉格朗日乘子 回归分析
在线阅读 下载PDF
多因素影响下双时间尺度退化设备剩余寿命预测 被引量:3
14
作者 耿鑫月 郑建飞 +2 位作者 胡昌华 李家垒 裴洪 《哈尔滨工程大学学报》 北大核心 2025年第9期1745-1753,共9页
针对双时间尺度退化设备在性能退化过程会受到内外部多重因素综合影响的问题,本文提出一种考虑多因素影响的剩余寿命预测方法。首先通过Transformer编码器学习单因素退化数据深层特征,然后将其输入到由Transformer网络构建的剩余寿命混... 针对双时间尺度退化设备在性能退化过程会受到内外部多重因素综合影响的问题,本文提出一种考虑多因素影响的剩余寿命预测方法。首先通过Transformer编码器学习单因素退化数据深层特征,然后将其输入到由Transformer网络构建的剩余寿命混合深度学习预测模型中,学习多因素数据间相关性及其中包含的寿命信息,进一步基于蒙特卡罗仿真获得剩余寿命预测结果的区间估计。通过锂电池的实例验证所提方法可以有效提高剩余寿命预测的精度。 展开更多
关键词 多因素影响 双时间尺度 Transformer网络 剩余寿命预测 不确定性量化 DROPOUT 蒙特卡罗仿真 随机退化
在线阅读 下载PDF
Fault Detection for Uncertain Delta Operator Systems with Two-Channel Packet Dropouts via a Switched Systems Approach 被引量:10
15
作者 ZHANG Duanjin ZHANG Yinshuang 《Journal of Systems Science & Complexity》 SCIE EI CSCD 2020年第5期1446-1468,共23页
This paper utilizes a switched systems approach to deal with the problem of fault detectio for uncertain delta operator networked control system with packet dropouts and timevarying delays.Uncertainties exist in the m... This paper utilizes a switched systems approach to deal with the problem of fault detectio for uncertain delta operator networked control system with packet dropouts and timevarying delays.Uncertainties exist in the matrices of the systems and are norm-bounded time-varying.Two parts of packet dropouts are considered in this paper:From sensors to controllers,and from controllers to actuators.Two independent Bernoulli distributed white sequences are introduced to account for packet dropouts.Then an FD filter is designed under an arbitrary switching law.Furthermore,the sufficient conditions for the NCSs under consideration that are exponentially stable in the mean-square sense and satisfy H∞performance are obtained in terms of linear matrix inequalitie,multiple Lyapunov function and average dwell-tim approach.The explicit expression of the desired filter parameters is given.Finally,a numerical example verifies the effectiveness of the proposed method. 展开更多
关键词 Delta operator fault detection networked control systems packet dropouts switched systems
原文传递
基于深度学习的小样本光学元件表面瑕疵识别
16
作者 邵延华 忻晨 楚红雨 《强激光与粒子束》 北大核心 2025年第12期1-8,共8页
针对小样本高功率固体激光装置中光学元件表面疵病的精准检测需求,基于ICFNet提出了一种融合数据增强与深度残差网络的检测方法ICFNetV2。首先采用残差连接机制与通道解耦卷积操作的协同设计,搭建了包含34个层级联模块的深度网络架构,... 针对小样本高功率固体激光装置中光学元件表面疵病的精准检测需求,基于ICFNet提出了一种融合数据增强与深度残差网络的检测方法ICFNetV2。首先采用残差连接机制与通道解耦卷积操作的协同设计,搭建了包含34个层级联模块的深度网络架构,成功抑制了深层网络训练中的梯度衰减现象,并显著提升了特征跨层传递效率。网络中嵌入了空间Dropout层,同时在数据预处理阶段采用随机旋转、镜像翻转和高斯噪声注入等数据增强策略,将训练样本量扩展至原始数据集的9倍,提升了模型的泛化能力。消融实验进一步证实网络中模块的有效性。实验结果表明,改进后的ICFNetV2在麻点、划痕和灰尘三类疵病分类任务中达到97.4%的准确率,相较ICFNet模型提升0.7%。 展开更多
关键词 精密光学元件 深度学习 ResNet 缺陷分类 小样本 DROPOUT
在线阅读 下载PDF
基于改进ResNet34网络模型的小麦籽粒种子分类研究
17
作者 薛淏 刘成忠 鲁清林 《软件工程》 2025年第10期22-25,共4页
针对传统小麦籽粒检测任务中种类少、数目小、识别效率不高、受数据集因素影响较大的问题,构建30000张小麦籽粒图像数据集进行分类研究。在原始ResNet34模型的残差结构中加入改进的SE-P注意力机制,减少无关的特征依赖,增强模型的特征表... 针对传统小麦籽粒检测任务中种类少、数目小、识别效率不高、受数据集因素影响较大的问题,构建30000张小麦籽粒图像数据集进行分类研究。在原始ResNet34模型的残差结构中加入改进的SE-P注意力机制,减少无关的特征依赖,增强模型的特征表达能力;在全连接层之前应用Dropout层,通过随机丢弃部分神经元,降低过拟合的发生。实验结果表明,改进后的ResNet34分类模型准确率、精确度和召回率分别为92.30%、92.23%和92.72%,相较于原模型准确率提升3.71%。在小麦籽粒分类任务中提升明显。 展开更多
关键词 小麦籽粒 ResNet34 Dropout层 SE-P注意力机制
在线阅读 下载PDF
人工智能在陆相低渗油田地质甜点预测的深度应用
18
作者 王宗俊 《同济大学学报(自然科学版)》 北大核心 2025年第8期1285-1299,共15页
为解决传统地球物理方法无法有效预测深层陆相低渗透甜点分布的局限性问题,提出了一套基于人工智能的高精度地质甜点预测方法流程,为压裂方案优化和开发井位部署提供可靠依据。通过多步骤人工智能算法,包括:XGBoost算法构建改进的低渗... 为解决传统地球物理方法无法有效预测深层陆相低渗透甜点分布的局限性问题,提出了一套基于人工智能的高精度地质甜点预测方法流程,为压裂方案优化和开发井位部署提供可靠依据。通过多步骤人工智能算法,包括:XGBoost算法构建改进的低渗储层经验性品质指数(RQI)、蜂群算法深度神经网络实现一维井点RQI曲线预测、基于随机失活策略的改进CNN算法,实现空间三维RQI展布预测,突破了传统甜点预测的局限性,实现了由一维到三维的多尺度智能预测,显著提升了低渗储层表征精度。某油田应用表明,该方法克服各不利因素影响,地质甜点预测精度较传统方法有明显提升。 展开更多
关键词 改进储层经验性品质指数 人工智能(AI) XGBoost 蜂群算法 随机失活(DropOut)
在线阅读 下载PDF
基于卷积神经网络的MNIST手写数字识别优化研究
19
作者 牟世桂 《计算机应用文摘》 2025年第3期81-83,86,共4页
文章旨在优化基于卷积神经网络的MNIST手写数字识别,通过引入残差连接、Dropout层、Batch Normalization层,以及优化算法与学习率调度器来提升模型性能。这些技术的综合应用旨在提高模型在数字识别任务中的精确度。其中,首先采用基于Res... 文章旨在优化基于卷积神经网络的MNIST手写数字识别,通过引入残差连接、Dropout层、Batch Normalization层,以及优化算法与学习率调度器来提升模型性能。这些技术的综合应用旨在提高模型在数字识别任务中的精确度。其中,首先采用基于ResNet结构的卷积神经网络,结合Dropout层、Batch Normalization层和残差连接来构建模型。其次,使用SGD优化算法配合学习率调度器和数据增强技术对模型进行训练和优化。研究结果表明,该模型在MNIST测试集上达到了99.5%的准确率,相比传统方法有了显著提升。这些成果不仅在提升数字识别的准确度上取得了显著进展,还证明了在实际应用中综合考虑优化算法、数据增强技术以及网络结构调整对于提升模型性能的重要性,对于推动图像识别技术的发展具有重要的应用价值和实际意义。 展开更多
关键词 MNIST CNN ResNet 模型优化 DROPOUT 学习率衰减
在线阅读 下载PDF
上一页 1 2 15 下一页 到第
使用帮助 返回顶部