526互联

Networks

Graph Convolutional Networks with EigenPooling

Ma Y., Wang S., Aggarwal C. C. and Tang J. Graph convolutional networks with eigenpooling. KDD, 2019. 概 本文提出了一种新的框架, 在前向的过程中, 可以逐步将相似的 nodes 和他们的特征聚合在 ......
Convolutional EigenPooling Networks Graph with

论文解读《Interpolated Adversarial Training: Achieving robust neural networks without sacrificing too much accuracy》

论文信息 论文标题：Interpolated Adversarial Training: Achieving robust neural networks without sacrificing too much accuracy论文作者：Alex LambVikas VermaKenji Kawa ......
Interpolated Adversarial sacrificing Achieving Training

Handling Information Loss of Graph Neural Networks for Session-based Recommendation

Chen T. and Wong R. C. Handling information loss of graph neural networks for session-based recommendation. KDD, 2020. 概 作者发现图用在 Session 推荐中存在: lossy ......
Recommendation Session-based Information Handling Networks

Series-Parallel Networks UVA - 10253

给定 n，求有多少树满足：任意非叶子节点的儿子不少于 2 ， 叶子节点个数为 n ......
Series-Parallel Parallel Networks Series 10253

EXPLORING MODEL-BASED PLANNING WITH POLICY NETWORKS

**发表时间：**2020（ICLR 2020） **文章要点：**这篇文章说现在的planning方法都是在动作空间里randomly generated，这样很不高效（其实瞎扯了，很多不是随机的方法啊）。作者提出在model based RL里用policy网络来做online planning ......
MODEL-BASED EXPLORING PLANNING NETWORKS POLICY

Cluster-GCN An Efficient Algorithm for Training Deep Convolution Networks

Chiang W., Liu X., Si S., Li Y., Bengio S. and Hsieh C. Cluster-GCN: An efficient algorithm for training deep and large graph convolutional networks. ......
Cluster-GCN Convolution Algorithm Efficient Training

Cycle GAN：Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks

paper：https://arxiv.org/pdf/1703.10593.pdf [2017] code 参考： https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix https://zhuanlan.zhihu.com/p/792211 ......
Cycle Image Cycle-Consistent Image-to-Image Adversarial

Spatiotemporal Remote Sensing Image Fusion Using Multiscale Two-Stream Convolutional Neural Networks

Spatiotemporal Remote Sensing Image Fusion Using Multiscale Two-Stream Convolutional Neural Networks abstract 地表反射率图像的渐变和突变是现有STF方法的主要挑战。(Gradual and ......
Spatiotemporal Convolutional Multiscale Two-Stream Networks

Invariant and Equivariant Graph Networks

Maron H., Ben-Hamu H., Shamir N. and Lipman Y. Invariant and equivariant graph networks. ICLR, 2019. 概 有些时候, 我们希望网络具有: 不变性 (Invariant): $$ f(PX) = f(X ......
Equivariant Invariant Networks Graph and

Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks

Zou D., Hu Z., Wang Y., Jiang S., Sun Y. and Gu Q. Layer-dependent importance sampling for training deep and large graph convolutional networks. NIPS, ......
Layer-Dependent Convolutional Importance Dependent Sampling

Multi-View Attribute Graph Convolution Networks for Clustering

论文阅读04-Multi-View Attribute Graph Convolution Networks for Clustering：MAGCN 论文信息 论文地址：Multi-View Attribute Graph Convolution Networks for Clustering | ......
Convolution Multi-View Clustering Attribute Networks

FastGCN Fast Learning with Graph Convolutional Networks via Importance Sampling

Chen J., Ma T. and Xiao C. FastGCN: fast learning with graph convolutional networks via importance sampling. ICLR, 2018. 概 一般的 GCN 每层通常需要经过所有的结点的 prop ......
Convolutional Importance Learning Networks Sampling

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning

Li Q., Han Z. and Wu X. Deeper insights into graph convolutional networks for semi-supervised learning. AAAI, 2018. 概 本文分析了 GCN 的实际上就是一种 Smoothing, 但是 ......
Semi-Supervised Convolutional Supervised Insights Networks

Stochastic Training of Graph Convolutional Networks with Variance Reduction

Chen J., Zhu J. and Song L. Stochastic training of graph convolutional networks with variance reduction. ICML, 2018. 概 我们都知道, GCN 虽然形式简单, 但是对于结点个数非常多的 ......
Convolutional Stochastic Reduction Networks Training

Squeeze-and-Excitation Networks（SENet）

结构和代码如下（参考：b站视频：YOLOv5 v6.1添加SE,CA,CBAM,ECA注意力机制教学，即插即用）： Global pooling：每个channel上面的所有点做平均，这样每个channel都输出一个数。所以左图中，HxWxC变成了1x1xC。（参考：关于global average ......
Squeeze-and-Excitation Excitation Networks Squeeze SENet

Do you know the bitwise sum sample demonstrated in "Neural Networks and Deep Learning" by autor Michael Nielsen?

Do you know the bitwise sum sample demonstrated in "Neural Networks and Deep Learning" by autor Michael Nielsen? Yes, I am familiar with the bitwise s ......
quot demonstrated Networks Learning bitwise

21An efficient message-authentication scheme based on edge computing for vehicular ad hoc networks

![](https://img2023.cnblogs.com/blog/1954056/202304/1954056-20230407164139367-1280910650.png) ![](https://img2023.cnblogs.com/blog/1954056/202304/1954... ......
message-authentication authentication efficient computing vehicular

迁移学习《Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks》

论文信息 论文标题：Pseudo-Label : The Simple and Efficient Semi-Supervised Learning Method for Deep Neural Networks论文作者：Dong-Hyun Lee论文来源：2013——ICML论文地址：downlo ......
Semi-Supervised Pseudo-Label Supervised Efficient Learning

Graph Neural Networks for Link Prediction with Subgraph Sketching

Chamberlain B. P., Shirobokov S., Rossi E., Frasca F., Markovich T., Hammerla N., Bronstein M. M. Hansmire M. Graph neural networks for link predictio ......
Prediction Sketching Networks Subgraph Neural

计网学习笔记五 wireless && mobile networks

老师把无线网络用一节课一遍过了…感觉没能学透，便课后自己总结，看书，找资料补充，把无线网络大概摸了个七七八八。虽然不算精细，但还能看！内容包括WLAN总概，WiFi—WLAN的实现，802.11规定的帧结构，以及蜂窝网络。 强烈推荐一本书：《802.11 Wireless Networks: The ......
amp wireless networks 笔记 mobile

Delphi 论文阅读 Delphi: A Cryptographic Inference Service for Neural Networks

摘要 许多公司为用户提供神经网络预测服务，应用范围广泛。然而，目前的预测系统会损害一方的隐私:要么用户必须将敏感输入发送给服务提供商进行分类，要么服务提供商必须将其专有的神经网络存储在用户的设备上。前者损害了用户的个人隐私，而后者暴露了服务提供商的专有模式。 我们设计、实现并评估了DELPHI，这是 ......
Delphi Cryptographic Inference Networks Service

Understanding plasticity in neural networks

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ Arxiv 2023 Abstract 可塑性是神经网络根据新信息快速改变预测的能力，对于深度强化学习系统的适应性和鲁棒性至关重要。众所周知，即使在相对简单的学习问题中，深度神经网络也会在训练过程中失去可塑性，但驱动这种现象的机制仍知之甚 ......
Understanding plasticity networks neural in

Going Deeper With Directly-Trained Larger Spiking Neural Networks

郑重声明：原文参见标题，如有侵权，请联系作者，将会撤销发布！ The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) Abstract 脉冲神经网络（SNN）在时空信息和事件驱动信号处理的生物可编程编码中很有前途，非 ......
Directly-Trained Directly Networks Trained Spiking
共113篇  :4/4页 首页上一页4下一页尾页