論文筆記之Learning Convolutional Neural Networks for Graphs
本篇論文是2016ICML上的一篇論文，對於如何將cnn應用在graph上提供了一種新的思路。web 架構： 整體上講，就是用w個固定size=（k+1）的子圖來表示輸入的graph，再將這w個子圖正則化後,生成一個w(k+1)維的向量，做爲傳統的cnn的輸入，進行學習。其實就是作了一個從graph到向量的映射的一個預處理過程。算法 算法流程 輸入：任意一張圖 輸出：每一個channel輸出w個r
相關文章
- 1. Learning Convolutional Neural Networks for Graphs論文筆記
- 2. Learning Convolutional Neural Networks for Graphs
- 3. 【Fast Algorithms for Convolutional Neural Networks】論文筆記
- 4. 【論文筆記】Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detecti
- 5. 論文閱讀筆記（一）：Learning Dual Convolutional Neural Networks for Low-Level Vision
- 6. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking 論文筆記
- 7. [論文筆記]Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
- 8. [論文筆記] [2016] [NIPS] Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- 9. Convolutional Networks on Graphs for Learning Molecular Fingerprints
- 10. 論文筆記：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- 更多相關文章...
- • ASP.NET Razor - 標記 - ASP.NET 教程
- • Scala for循環 - Scala教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • 互聯網組織的未來：剖析GitHub員工的任性之源
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Learning Convolutional Neural Networks for Graphs論文筆記
- 2. Learning Convolutional Neural Networks for Graphs
- 3. 【Fast Algorithms for Convolutional Neural Networks】論文筆記
- 4. 【論文筆記】Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detecti
- 5. 論文閱讀筆記（一）：Learning Dual Convolutional Neural Networks for Low-Level Vision
- 6. Learning Multi-Domain Convolutional Neural Networks for Visual Tracking 論文筆記
- 7. [論文筆記]Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
- 8. [論文筆記] [2016] [NIPS] Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
- 9. Convolutional Networks on Graphs for Learning Molecular Fingerprints
- 10. 論文筆記：Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering