论文笔记之Learning Convolutional Neural Networks for Graphs
本篇论文是2016ICML上的一篇论文，对于如何将cnn应用在graph上提供了一种新的思路。web 架构： 整体上讲，就是用w个固定size=（k+1）的子图来表示输入的graph，再将这w个子图正则化后,生成一个w(k+1)维的向量，做为传统的cnn的输入，进行学习。其实就是作了一个从graph到向量的映射的一个预处理过程。算法 算法流程 输入：任意一张图 输出：每一个channel输出w个r
相关文章
- 1. Learning Convolutional Neural Networks for Graphs论文笔记
- 2. Learning Convolutional Neural Networks for Graphs
- 3. 【Fast Algorithms for Convolutional Neural Networks】论文笔记
- 4. 【论文笔记】Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detecti
- 5. 论文阅读笔记（一）：Learning Dual Convolutional Neural Networks for Low-Level Vision
- 6. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking 论文笔记
- 7. [论文笔记]Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
- 8. [论文笔记] [2016] [NIPS] Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- 9. Convolutional Networks on Graphs for Learning Molecular Fingerprints
- 10. 论文笔记：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- 更多相关文章...
- • ASP.NET Razor - 标记 - ASP.NET 教程
- • Scala for循环 - Scala教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • 互联网组织的未来：剖析GitHub员工的任性之源
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. Learning Convolutional Neural Networks for Graphs论文笔记
- 2. Learning Convolutional Neural Networks for Graphs
- 3. 【Fast Algorithms for Convolutional Neural Networks】论文笔记
- 4. 【论文笔记】Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detecti
- 5. 论文阅读笔记（一）：Learning Dual Convolutional Neural Networks for Low-Level Vision
- 6. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking 论文笔记
- 7. [论文笔记]Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
- 8. [论文笔记] [2016] [NIPS] Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- 9. Convolutional Networks on Graphs for Learning Molecular Fingerprints
- 10. 论文笔记：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering