使用seq2point神经网络进行点对点学习以进行非侵入式负载监测

一本非常经典的卡尔曼滤波教程，适合中高等的研究人员参考

CS229 2018年秋季 斯坦福大学的课程的所有讲义，幻灯片和作业。 所有讲座的视频都可以 。

Spam Review Detection with Graph Convolutional Networks

堆叠沙漏模型：TensorFlow实现 A.Newell等人的用于人体姿势估计的堆叠沙漏网络的Tensorflow实现。 代码作为MSc Computing个人项目的一部分（伦敦帝国学院2017年） 基于 -A.Newell等 -肖楚等。 -可用（重型型号） 状态 这是一个WIP回购 已测试人体姿势 效率（在较轻的模型上工作） 数据生成器完成（在协议缓冲区上工作） 多人姿势估计（尝试实现固定帧速率） 目前接受过培训 配置文件 目录中有一个``config.cgf''，其中包含调整模型所需的所有变量。 training_txt_file : Path to TEXT file cont

Networks: An Introduction Oxford University Press, 2010-3-25 名称 Networks: An Introduction 作者 Mark E. J. Newman 版本 插图版, 再版 出版商 Oxford University Press, 2010 ISBN 0199206651, 9780199206650 页数 772 页

Graphs are useful data structures in complex real-life applications such as modeling physical systems, learning molecular fingerprints, controlling traffic networks, and recommending friends in social networks. However, these tasks require dealing with non-Euclidean graph data that contains rich relational information between elements and cannot be well handled by traditional deep learning models (e.g., convolutional neural networks (CNNs) or recurrent neural networks (RNNs)). Nodes in graphs usually contain useful feature information that cannot be well addressed in most unsupervised representation learning methods (e.g., network embedding methods). Graph neural networks (GNNs) are proposed to combine the feature information and the graph structure to learn better representations on graphs via feature propagation and aggregation. Due to its convincing performance and high interpretability, GNN has recently become a widely applied graph analysis tool.

The main purpose of this book is to present basic principles and methods for developing optimization models for contemporary communication and computer network design. The book is focused on optimization problems and methods for traffic routing, flow, and resource capacity optimization. We aim at developing a general framework applicable to such technologies as IP, IDN, MPLS, ATM, SONET/SDH, and WDM, and capable to cope with new network technologies that will emerge in the future.

Lambda网络-Pytorch λ网络的实现，这是ImageNet上达到SOTA的一种新的图像识别方法。 新方法利用λ层，该层通过将上下文转换为称为lambda的线性函数并将这些线性函数分别应用于每个输入来捕获交互。 安装 $ pip install lambda-networks 用法 全球背景 import torch from lambda_networks import LambdaLayer layer = LambdaLayer ( dim = 32 , # channels going in dim_out = 32 , # channels

描述IGP的经典书籍，CCIE 之路必备资料。