Densely connected neural networks for nonlinear regression
School of Mathematical and Statistical Sciences, Clemson University(克莱姆森大学数学与统计科学学院);Faculty of Engineering, Monash University(莫纳什大学工程学院);Faculty of Information Technology, Monash University(莫纳什大学信息技术学院);Institute of Atmospheric Physics, Chinese Academy of Sciences(中国科学院大气物理研究所)
Densely connected convolutional networks (DenseNet) behave well in image processing. However, for regression tasks, convolutional DenseNet may lose essential information from independent input features. To tackle this issue, we propose a novel DenseNet regression model where convolution and pooling layers are replaced by fully connected layers and the original concatenation shortcuts are maintained to reuse the feature. To investigate the effects of depth and input dimension of proposed model, careful validations are performed by extensive numerical simulation. The results give an optimal depth (19) and recommend a limited input dimension (under 200). Furthermore, compared with the baseline models including support vector regression, decision tree regression, and residual regression, our proposed model with the optimal depth performs best. Ultimately, DenseNet regression is applied to predict relative humidity, and the outcome shows a high correlation (0.91) with observations, which indicates that our model could advance environmental data analysis.
Densely Connected Residual Network for Attack Recognition
University of New South Wales(新南威尔士大学);Australian Center for Cyber, University of New South Wales(新南威尔士大学澳大利亚网络中心);Sangfor Technologies Inc.(深信服科技股份有限公司)
Densely Connected Recurrent Residual (Dense R2UNet) Convolutional Neural Network for Segmentation of Lung CT Images
Washington University School of Medicine(华盛顿大学医学院)
深度学习网络已经为语义分割提供了最先进的性能。这些技术被广泛应用于医学检测、分割和分类。基于U-Net的架构的出现对于该应用已经变得特别流行。本文提出了基于U-Net模型结构的递归残差卷积神经网络(Dense R2 U CNN),它是递归CNN、残差网络和稠密卷积网络的综合。残差单元有助于训练更深的网络,而密集的递归层增强了分割所需的特征传播。在基准肺部病变数据集上测试的所提出的模型在分割任务上表现出比其等效模型更好的性能。
Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
College of Computer Science, Nankai University(南开大学计算机学院);ETH Zurich(苏黎世联邦理工学院);School of Information and Communication Engineering, University of Electronic Science and Technology of China(电子科技大学信息与通信工程学院)
Three-Dimensional Radiotherapy Dose Prediction on Head and Neck Cancer Patients with a Hierarchically Densely Connected U-net Deep Learning Architecture
University of Texas Southwestern Medical Center(德克萨斯大学西南医学中心)
Optimizing Federated Graph Learning with Inherent Structural Knowledge and Dual-Densely Connected GNNs
Xidian University(西安电子科技大学);University of Science and Technology of China(中国科学技术大学);The University of Electro-Communications(电气通信大学);Hefei University of Technology(合肥工业大学)
DCC: A Cascade based Approach to Detect Communities in Social Networks
National Institute of Technology Silchar(西尔查尔国家理工学院);Eindhoven University of Technology(埃因霍温理工大学)
社交网络中的社区发现与发现和分组网络中固有的最相似的节点相关联。这些相似的节点通过计算结强度来识别。更强的关系表示连接的节点对共享的更高的邻近度。这项工作的动机是格兰米特的论点,表明强关系在于密集连接的节点和理论,社区核心在现实世界的网络是密集连接的。在本文中,我们介绍了一种新的方法称为\emph{Disjoint Community detection using Cascades (DCC)},它证明了一个新的局部密度为基础的连接强度测量检测社区的有效性。在这里,利用联系强度来决定传播信息所遵循的路径。其思想是通过不断增加的联系强度引导,通过级联的元组信息向社区核心爬行。考虑到级联生成的步骤,一种新的优先成员资格的方法已经被开发来分配社区标签未分配的节点。$DCC$的有效性已经基于几个真实世界数据集和基线社区发现算法的质量和准确性进行了分析。
NVIDIA(英伟达);Imperial College London(帝国理工学院);Carnegie Mellon University(卡内基梅隆大学);Amazon AI(亚马逊人工智能);University of Southern California(南加州大学);California Institute of Technology(加州理工学院)