大数据机器学习实验室-CSDN博客

原创【论文翻译】Deep Residual Learning for Image Recognition

论文题目：Deep Residual Learning for Image Recognition论文来源：Deep Residual Learning for Image Recognition翻译人：BDML@CQUT实验室Deep Residual Learning for Image RecognitionKaiming He & Xiangyu Zhang & Shaoqing Ren & Jian Sun 图像识别领域的深度残差学习Kaiming He &am

2020-08-28 16:10:57 1367

翻译【论文翻译】Focal Loss for Dense Object Detection

论文题目：Focal Loss for Dense Object Detection论文来源：Focal Loss for Dense Object Detection摘要迄今为止，精度最高的目标检测器是基于R-CNN推广的两阶段方法，其中分类器应用于稀疏的候选对象位置集。相比之下，在可能的物体位置的规则，密集采样上应用的 one-stage 探测器具有更快和更简单的可能性，但迄今为止已经落后于 two-stage 探测器的精度。在本文中，我们将探讨为什么会出现这种情况。我们发现在密集型探测器训练过程

2020-08-27 23:14:12 3489

原创【论文翻译】Machine learning: Trends, perspectives, and prospects

论文题目：Machine learning: Trends, perspectives, and prospects论文来源：Machine learning: Trends, perspectives, and prospects_2015_Science翻译人：BDML@CQUT实验室**Machine learning:Trends,perspectives, and prospectsM. I. Jordan1* and T. M. Mitchell2*AbstractMachine l

2020-08-27 12:25:31 1141

原创 [论文翻译]Clustering by Passing Messages Between Data Points

【论文题目】：Clustering by Passing Messages Between Data Points【论文来源】：Clustering by Passing Messages Between Data Points【翻译人】：BDML@CQUT实验室Clustering by Passing Messages Between Data Points通过在数据点之间传递信息进行聚类处理Brendan J. Frey and Delbert Dueck*Clustering data

2020-08-27 10:57:56 557

原创【论文翻译】Nonlinear Dimensionality Reduction by Locally Linear Embedding

论文题目：Nonlinear Dimensionality Reduction by Locally Linear Embedding论文来源：Nonlinear Dimensionality Reduction by Locally Linear Embedding翻译人：BDML@CQUT实验室Nonlinear Dimensionality Reduction by Locally Linear Embedding基于局部线性嵌入的非线性降维方法Sam T. Roweis and Lawre

2020-08-26 21:22:00 391

原创【论文翻译】Deep learning

【论文题目】：Deep learning【论文来源】：Deep learning【翻译人】：BDML@CQUT实验室Deep learningYann LeCun, Yoshua Bengio& Geoffrey Hinton深度学习AbstractDeep learning allows computational models that are composed of multiple processing layers to learn representations of da

2020-08-26 16:33:58 1155

翻译【论文翻译】Machine learning: Trends, perspectives, and prospects

论文题目：Machine learning: Trends, perspectives, and prospects论文来源：Machine learning: Trends, perspectives, and prospects【论文翻译】Machine learning: Trends, perspectives, and prospects机器学习：趋势、观点和展望M. I. Jordan * and T. M. Mitchell *AbstractMachine learning ad

2020-08-25 21:59:13 319

翻译【论文翻译】卷积神经网络研究综述

卷积神经网络研究综述Review of Convolutional Neural Network周飞燕金林鹏董军摘要作为一个十余年来快速发展的崭新领域，深度学习受到了越来越多研究者的关注，它在特征提取和模型拟合上都有着相较于浅层模型显然的优势。深度学习善于从原始输入数据中挖掘越来越抽象的分布式特征表示，而这些表示具有良好的泛化能力。它解决了过去人工智能中被认为难以解决的一些问题。且随着训练数据集数量的显著增长以及芯片处理能力的剧增，它在目标检测和计算机视觉、自然语言处理、语音识别和语义分析

2020-08-25 20:23:24 10707

原创【论文翻译】Clustering by Passing Messages Between Data Points

【论文题目】：Clustering by Passing Messages Between Data Points【论文来源】：Clustering by Passing Messages Between Data Points【翻译人】：BDML@CQUT实验室Clustering by Passing Messages Between Data Points通过在数据点之间传递消息进行聚类Brendan J. Frey* and Delbert DueckAbstractCl

2020-08-25 17:31:16 265

翻译【论文翻译】Machine learning: Trends, perspectives, and prospects_2

论文题目：Machine learning: Trends, perspectives, and prospects翻译人：BDML@CQUT实验室Machine learning: Trends, perspectives, and prospects机器学习：趋势、观点和前景 M. I. Jordan* and T. M. Mitchell*AbstractMachine learning addresses the question of how to build computers th

2020-08-23 19:20:27 594

原创 [论文翻译] A Global Geometric Framework for Nonlinear Dimensionality Reduction

[论文翻译] A Global Geometric Framework for Nonlinear Dimensionality Reduction论文题目：A Global Geometric Framework for Nonlinear Dimensionality Reduction论文来源：A Global Geometric Framework for Nonlinear Dimensionality Reduction翻译人：BDML@CQUT实验室A Global Geometric

2020-08-22 15:48:13 1091

翻译 [论文翻译]Reducing the Dimensionality of Data with Neural Networks

论文来源:Reducing the Dimensionality of Data with Neural Networks通过训练一个具有小中心层的多层神经网络重构高维输入向量，可以将高维数据转换为低维码。梯度下降可以用来微调这种“自动编码器”网络的权值，但只有当初始权值接近一个好的解决方案时，这种方法才能很好地工作。我们描述了一种有效的初始化权值的方法，它允许深度自动编码器网络学习低维数据，这比主成分分析降维效果更好。降维能有效的促进高维数据的分类、可视化、通信和存储。主成分分析(PCA)是一种简单而

2020-08-20 22:02:34 810

原创【论文翻译】A Global Geometric Framework for Nonlinear Dimensionality Reduction

论文题目：A Global Geometric Framework for Nonlinear Dimensionality Reduction论文来源:https://www.sci-hub.ren/10.2307/3081721A Global Geometric Framework for Nonlinear Dimensionality Reduction非线性降维的全局几何框架Joshua B. Tenenbaum,1 Vin de Silva,2 John C. Langford3*A

2020-08-20 16:25:52 338

原创【论文翻译】Clustering by Passing Messages Between Data Points

【论文题目】：Clustering by Passing Messages Between Data Points【论文来源】：Clustering by Passing Messages Between Data Points【翻译人】：BDML@CQUT实验室Clustering by Passing Messages Between Data PointsBrendan J. Frey*, Delbert Dueck通过在数据点之间传递消息进行聚类AbstractClustering d

2020-08-20 12:35:19 419

原创 [论文翻译]Reducing the Dimensionality of Data with Neural Networks

论文题目：Reducing the Dimensionality of Data with Neural Networks论文来源：10.1126/science.1127647翻译人：BDML@CQUT实验室Reducing the Dimensionality of Data with Neural Networks利用神经网络降低数据的维度G. E. Hinton* and R. R. SalakhutdinovHigh-dimensional data can be converted

2020-08-20 11:27:03 4045

原创【论文翻译】Nonlinear Dimensionality Reduction by Locally Linear Embedding

论文题目：Nonlinear Dimensionality Reduction by Locally Linear Embedding论文来源：Nonlinear Dimensionality Reduction by Locally Linear Embedding翻译人：BDML@CQUT实验室Nonlinear Dimensionality Reduction by Locally Linear EmbeddingSam T. Roweis and Lawrence K. Saul通过局部线

2020-08-20 10:17:46 308

原创【论文翻译】Deep Residual Learning for Image Recognition

论文题目：Deep Residual Learning for Image Recognition论文来源：Deep Residual Learning for Image Recognition翻译人：BDML@CQUT实验室Deep Residual Learning for Image Recognition深度残差学习用于图像识别Kaiming He Xiangyu Zhang Shaoqing Ren Jian SunMicrosoft Research{kahe, v-xiangz

2020-08-19 20:45:40 240

原创【论文翻译】Clustering by Passing Messages Between Data Points

【论文题目】：Clustering by Passing Messages Between Data Points【论文来源】：Clustering by Passing Messages Between Data Points【翻译人】：BDML@CQUT实验室Clustering by Passing Messages Between Data PointsBrendan J. Frey* and Delbert Dueck通过在数据点之间传递消息进行聚类AbstractClusterin

2020-08-19 17:08:08 697

翻译 Deep learning翻译

Deep learningYann LeCun, Yoshua Bengio& Geoffrey Hinton 深度学习Yann LeCun, Yoshua Bengio& Geoffrey HintonAbstract Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with .

2020-08-19 17:02:45 1862

翻译【论文翻译】Clustering by fast search and find of density peaks

Clustering by fast search and find of density peaks基于快速搜索和密度峰发现的聚类方法Alex Rodriguez and Alessandro LaioCluster analysis is aimed at classifying elements in to categories on the basis of their similarity. Its applications range from astronomy to bioinform

2020-08-18 23:27:15 3948

原创【翻译】Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector论文翻译

2020CVPR Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector

2020-08-18 21:24:34 1242

原创【论文翻译】聚类算法研究

论文题目：聚类算法研究论文来源：聚类算法研究翻译人：BDML@CQUT实验室聚类算法研究孙吉贵 , 刘杰 , 赵连宇Clustering Algorithms ResearchSUN Ji-Gui, LIU Jie, ZHAO Lian-Yu摘要对近年来聚类算法的研究现状与新进展进行归纳总结.一方面对近年来提出的较有代表性的聚类算法,从算法思想、关键技术和优缺点等方面进行分析概括;另一方面选择一些典型的聚类算法和一些知名的数据集,主要从正确率和运行效率两个方面进行模拟实验,并分别就同一种

2020-08-18 20:02:06 13763

原创【论文翻译】Nonlinear Dimensionality Reduction by Locally Linear Embedding

论文题目：Nonlinear Dimensionality Reduction by Locally Linear Embedding论文来源：Nonlinear Dimensionality Reduction by Locally Linear Embedding翻译人：BDML@CQUT实验室Nonlinear Dimensionality Reduction by Locally Linear Embedding基于局部线性嵌入的非线性降维方法Sam T. Roweis1 and

2020-08-18 17:45:54 363

原创【论文翻译】Deep Residual Learning for Image Recognition

【论文翻译】Deep Residual Learning for Image Recognition【论文题目】Deep Residual Learning for Image Recognition【翻译人】Deep Residual Learning for Image Recognition[译]基于深度残差学习的图像识别2016 IEEE Conference on Computer Vision and Pattern RecognitionKaiming He Xiangyu Zh

2020-08-18 12:56:43 395

原创【论文翻译】 Clustering by Passing Messages Between Data Points

论文题目：Clustering by Passing Messages Between Data Points论文来源：Clustering by Passing Messages Between Data Points翻译人：BDML@CQUT实验室Clustering by Passing Messages Between Data PointsBrendan J. Frey* and Delbert Dueck通过在数据点之间传递消息进行聚类Brendan J. Frey* and Del

2020-08-18 11:43:23 406

翻译【论文翻译】Machine learning: Trends, perspectives, and prospects

Machine learning: Trends, perspectives, and prospectsM. I. Jordan* and T. M. Mitchell*机器学习：趋势、观点和前景Abstract： Machine learning addresses the question of how to build computers that improve automatically through experience. It is one of today’s most rapid

2020-08-17 22:49:36 970

原创 [论文翻译] Clustering by Passing Messages Between Data Points

[论文翻译] Clustering by Passing Messages Between Data Points论文题目：Clustering by Passing Messages Between Data Points论文来源：Clustering by Passing Messages Between Data Points翻译人：BDML@CQUT实验室Clustering by Passing Messages Between Data PointsBrendan J. Frey* a

2020-08-17 18:44:52 360

原创 OSNet 论文翻译

OSNet 论文翻译摘要作为一个实例级的识别问题，行人再识别(ReID)依赖于具有识别能力的特征，它不仅能捕获不同的空间尺度，还能封装多个尺度的任意组合。我们称这些同构和异构尺度的特征为全尺度特征。本文设计了一种新颖的深度CNN，称为全尺度网络(OSNet)，用于ReID的全尺度特征学习。这是通过设计一个由多个卷积特征流组成的残差块来实现的，每个残差块检测一定尺度的特征。重要的是，引入了一种新的统一聚合门用输入依赖的每个channel权重进行动态多尺度特征融合。为了有效地学习空间通道相关性，避免过度拟合

2020-08-17 17:45:32 2130

原创 Machine learningTrends, perspectives, and prospects

论文翻译：Machine learning:Trends, perspectives, and prospects机器学习：趋势，视角和前景Abstract摘要Machine learning addresses the question of how to build computers that improveautomatically through experience. It is one of today’s most rapidly growing technical fields

2020-08-16 22:50:24 1264

翻译针对图像识别的深度残差学习 Deep Residual Learning for Image Recognition ResNet

请配合原文食用。文中没有截图。有的翻译可能没有严格按照原文的词义来翻译，中英文的翻译重在意思，词义强引可能造成奇怪的感觉。有的段落不通顺不懂，可能需要结合原文和相关图表才好理解。每个人对英文感觉都不一样，所以请配合原文食用，文章仅仅帮助辅助理解。---l针对图像识别的深度残差学习摘要：更深的神经网络更难训练，我们提出了一个残差学习框架来减轻网络的训练，这个框架比以往使用过的网络在深得更彻底。我们将这些层明确地重定义为参照前一层的残差学习函数。而不是学习无参照的函数。我们提供全面的经验证据来展示这些残

2020-08-16 17:58:02 1289

原创【翻译】Deep Residual Learning for Image Recognition论文翻译

【论文翻译】：Deep Residual Learning for Image Recognition【论文来源】：Deep Residual Learning for Image Recognition【翻译人】：BDML@CQUT实验室Deep Residual Learning for Image Recognition基于深度残差学习的图像识别2016 IEEE Conference on Computer Vision and Pattern Recognition图像识别的深度残差学

2020-08-15 15:58:54 476

翻译 [论文翻译]Deep Learning

论文来源:Deep learningDeep LearningYann LeCun, Yoshua Bengio & Geoffrey HintonAbstractDeep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These

2020-08-15 02:19:37 665

翻译【论文翻译】Fully Convolutional Networks for Semantic Segmentation_2

论文题目：Fully Convolutional Networks for Semantic Segmentation论文来源:Fully Convolutional Networks for Semantic Segmentation_2015_CVPR翻译人：BDML@CQUT实验室Fully Convolutional Networks for Semantic Segmentation 用于语义分割的全卷积网络 Jonathan Long∗ Evan Shelhamer∗

2020-08-14 19:12:53 788

原创 Deep Residual Learning for Image Recognition

Deep Residual Learning for Image RecognitionKaiming He Xiangyu Zhang Shaoqing Ren Jian Sun基于深度残差学习的图像识别Kaiming He Xiangyu Zhang Shaoqing Ren Jian SunAbstractDeeper neural networks are more difficult to train. We present a residual learning framewor

2020-08-14 15:22:44 412

原创【论文翻译】Nonlinear Dimensionality Reduction by Locally Linear Embedding

论文题目：Nonlinear Dimensionality Reduction by Locally Linear Embedding论文来源：http://science.sciencemag.org/Nonlinear Dimensionality Reduction by Locally Linear Embedding通过局部线性嵌入减少非线性维数Sam T. Roweis1 and Lawrence K. Saul2AbstractMany areas of science depen

2020-08-14 12:14:11 231

原创 Clustering by Passing Messages Between Data Points

Clustering by Passing MessagesBetween Data PointsBrendan J. Frey* and Delbert Dueck通过在数据点之间传递消息进行聚类摘要:Clustering data by identifying a subset of representative examples is important for processing sensory signals and detecting patterns in data. Such “

2020-08-14 11:21:59 319

原创【论文翻译】Clustering by Passing Messages Between Data Points

论文题目：Clustering by Passing Messages Between Data Points论文来源：Clustering by Passing Messages Between Data Points翻译人：BDML@CQUT实验室Clustering by Passing Messages Between Data PointsBrendan J. Frey* and Delbert Dueck通过在数据点之间传递消息进行聚类Brendan J. Frey* and Del

2020-08-13 23:20:21 296

原创【论文翻译】Machine learning: Trends, perspectives, and prospects

论文题目：Machine learning- Trends, perspectives, and prospects论文来源:Machine learning: Trends, perspectives, and prospects_2015_Science翻译人：BDML@CQUT实验室Machine learning- Trends, perspectives, and prospectsM. I. Jordan1* and T. M. Mitchell2*导读Despite practic

2020-08-13 20:34:03 471

原创 [论文翻译] Machine learning: Trends, perspectives, and prospects

[论文题目]：Machine learning: Trends, perspectives, and prospects[论文来源]：Machine learning: Trends, perspectives, and prospects[翻译人]：BDML@CQUT实验室Machine learning:Trends,perspectives, and prospects机器学习：趋势、观点和前景M. I. Jordan1* and T. M. Mitchell2*AbstractMach

2020-08-13 16:47:57 1065

原创【论文翻译】Deep Residual Learning for Image Recognition

DeepResidualLearningforImageRecognition基于深度残差学习的图像识别AbstractDeeper neural networks are more difﬁcult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explici

2020-08-13 15:41:17 1271

java连接数据库实现增删改查 教师管理系统

java连接mysql数据库 增删改查

空空如也

java连接数据库实现增删改查教师管理系统

java连接mysql数据库增删改查