• 投稿

【双语字幕】宾夕法尼亚大学《图神经网络》课程(2020) by Alejandro RIbeiro

3.0万
76
2020-10-05 22:24:53
748
340
3269
197
https://gnn.seas.upenn.edu/ Graph Neural Networks (ESE680) Home:https://gnn.seas.upenn.edu/
AI
机器学习
深度学习
爱可可-爱生活 发消息
新浪微博 @爱可可-爱生活 http://weibo.com/fly51fly
视频选集
（1/80）
自动连播
Lecture 1.1 - Graph Neural Networks
06:37
Lecture 1.2 - Machine Learning on Graphs- The Why
07:26
Lecture 1.3 - Machine Learning on Graphs- The How
03:36
Lecture 1.4 - Convolutions in time, in space, and on graphs
10:54
Lecture 1.5 - Convolutional Neural Networks and Graph Neural Networks
07:52
Lecture 1.6 - The Road Ahead
04:07
Lecture 2.1 - Artificial Intelligence as Statistical Learning
08:08
Lecture 2.2 - A Word on Models
03:54
Lecture 2.3 - Empirical Risk Minimization
05:46
Lecture 2.4 - Learning Parameterizations
07:24
Lecture 2.5 - Stochastic Gradient Descent
08:18
Lecture 2.6 - Stochastic Gradient Descent Memorabilia
07:52
Lecture 2.7 - The Importance of Learning Parametrizations
10:41
Lecture 3.1 - Graphs
05:55
Lecture 3.2 - Graph Shift Operators
10:08
Lecture 3.3 - Graph Signals
09:20
Lecture 3.4 - Graph Convolutional Filters
09:18
Lecture 3.5 - Time Convolutions and Graph Convolutions
10:21
Lecture 3.6 - Graph Fourier Transform
04:12
Lecture 3.7 - Graph Frequency Response
08:41
Lecture 4.1 - Learning with Graph Signals
08:25
Lecture 4.2 - Graph Neural Networks (GNNs)
14:35
Lecture 4.3 - Observations about GNNs
09:14
Lecture 4.4 - Fully Connected Neural Networks (FCNNs)
06:57
Lecture 4.5 - GNNs vs FCNNs
06:00
Lecture 4.6 - Graph Filter Banks
14:46
Lecture 4.7 - Multiple Feature GNNs
12:30
Lecture 5.1 – Permutation Equivariance of Graph Filters
11:17
Lecture 5.2 - Permutation Equivariance of Graph Neural Networks
13:40
Lecture 5.3 - Lipschitz and Integral Lipschitz Filters
11:13
Lecture 5.4 - Stability of Graph Filters to Scaling
16:04
Lecture 5.5 - Stability of Graph Neural Networks to Scaling
12:25
Lecture 6.1 - Additive Perturbations of Graph Filters
09:27
Lecture 6.2 - Stability of Lipschitz Filters to Additive Perturbations
09:37
Lecture 6.3 - Relative Perturbations of Graph Filters
08:33
Lecture 6.4 - Stability of Integral Lipschitz Filters to Relative Perturbations
09:05
Lecture 6.5 - Stability Properties of Graph Neural Networks
10:23
Lecture 6.6 - GNNs Inherit the Stability Properties of Graph Filters
11:23
Lecture 7.1 - Definitions
07:10
Lecture 7.2 - Eigenvector Perturbation Lemma
05:51
Lecture 7.3 - From Shift to Filter Perturbations
07:01
Lecture 7.4 - Shifting to the GFT Domain
07:19
Lecture 7.5 - Proof of Fact 1
09:57
Lecture 7.6 - Proof of Fact 2
10:22
Lecture 8.1 - First Midterm
09:14
Lecture 8.2 - Learning Ratings in Recommendation Systems
06:11
Lecture 8.3 - Learning Ratings with Graph Filters and GNNs
04:44
Lecture 8.4 - Permutation Equivariance
06:57
Lecture 8.5 - Stability of Graph Filters to Graph Perturbations
06:24
Lecture 8.6 - Stability and Discriminability are Incompatible in Graph Filters
08:53
Lecture 8.7 - The Stability vs Discriminability Tradeoff of GNNs
09:00
Lecture 8.8 - Equivariance, Stability, and Transference
04:05
Lecture 9.1 - Definitions and Examples
08:41
Lecture 9.2 - Convergence of Graph Sequences
11:11
Lecture 9.3 - Graphon Signals
07:24
Lecture 9.4 - Graphon Fourier Transform (WFT)
09:57
Lecture 9.5 - The GFT converges to the WFT
12:11
Lecture 9.6 - Graphon Filters
06:50
Lecture 10.1 - Convergence of Graph Filters in the Spectral Domain
06:01
Lecture 10.2 - Convergence of Graph Filters in the node Domain
07:48
Lecture 10.3 - Graphon Filters are Generative Models for Graph Filters
16:07
Lecture 10.4 - Transferability of Graph Filters- Theorem
06:28
Lecture 10.5 - Transferability of Graph Filters- Remarks
07:47
Lecture 10.6 - Transferability of GNNs
13:48
Lecture 11.1 - Machine Learning on Sequences
08:22
Lecture 11.2 - Recurrent Neural Networks
08:57
Lecture 11.3 - Time Gating
07:17
Lecture 11.4 - Graph Recurrent Neural Networks
07:05
Lecture 11.5 - Spatial Gating
09:13
Lecture 11.6 - Stability of GRNNs
03:55
Lecture 11.7 - Epidemic Modeling with GRNNs
06:26
Lecture 12.1 - Linear Algebra
14:02
Lecture 12.2 - Algebraic Signal Processing
12:07
Lecture 12.3 - Polynomials in an Algebra and Polynomial Functions
08:09
Lecture 12.4 - Generators, Shift Operators and Frequency Representations
20:51
Lecture 12.5 - Convolutional Information Processing
11:13
Lecture 12.6 - Algebraic Neural Networks
06:24
Lecture 12.7 - Perturbation Models
06:14
Lecture 12.8 - Stability Theorems
09:09
Lecture 12.9 - Spectral Representations
09:32

【B站AI论坛】欢迎写代码、做产品的AI开发者发帖加入
共建AI开发者交流地>>

【双语字幕】MIT《数据分析、信号处理和机器学习中的矩阵方法》课程 (Spring 2018) by Gilbert Strang
爱可可-爱生活
14.7万 618

【双语字幕】斯坦福CS231n《深度视觉识别》课程(2017) by Fei-Fei Li, Justin Johnson, Serena Yeung
爱可可-爱生活
21.8万 3528

北邮《Python编程与实践》课程 (2020)
爱可可-爱生活
18.9万 3881

【双语字幕】哈佛大学《心理学导论》课程(2021) by Steven Pinker
爱可可-爱生活
34.0万 1689

【双语字幕】斯坦福CS224W《图机器学习》课程(2021) by Jure Leskovec
爱可可-爱生活
13.6万 1112

李宏毅深度强化学习(国语)课程(2018)
爱可可-爱生活
23.8万 2521

李宏毅《深度学习人类语言处理》国语课程(2020)
爱可可-爱生活
6.8万 977

【双语字幕】斯坦福CS224n《深度学习自然语言处理》课程(2019) by Chris Manning
爱可可-爱生活
9.9万 1153

AI第一性原理
爱可可-爱生活
1493 0

林轩田机器学习基石(国语)
爱可可-爱生活
43.9万 8004

AI让人类变强了吗？一场关于进化的错觉
爱可可-爱生活
1595 0

AI裁员陷阱：一场所有人都在输的理性游戏
爱可可-爱生活
4000 7

李宏毅深度学习(2017)
爱可可-爱生活
45.2万 6094

李宏毅《机器学习/深度学习》国语课程(2021)
爱可可-爱生活
7.0万 440

【双语字幕】给宝宝看的神经网络书
爱可可-爱生活
11.8万 132

AI时代，什么工作最值钱？
爱可可-爱生活
1250 0

哈佛大学CS50《计算机导论》课程(2019)
爱可可-爱生活
20.7万 1726

AI怎么学会举一反三？——泛化的秘密
爱可可-爱生活
1258 0

别让AI“看图说瞎话”——图表类学科的AI教学突破指南
爱可可-爱生活
1445 0

人类 vs AI：一场根本不存在的战争
爱可可-爱生活
2000 2
展开
所有瓦友，点击参与投票！
客服
顶部
赛事库 课堂 2021拜年纪