Xavier Bresson: "Convolutional Neural Networks on Graphs"
New Deep Learning Techniques 2018
"Convolutional Neural Networks on Graphs"
Xavier Bresson, Nanyang Technological University, Singapore
Abstract: Convolutional neural networks have greatly improved state-of-the-art performances in computer vision and speech analysis tasks, due to its high ability to extract multiple levels of representations of data. In this talk, we are interested in generalizing convolutional neural networks from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, telecommunication networks, or words' embedding. We present a formulation of convolutional neural networks on graphs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Numerical experiments demonstrate the ability of the system to learn local stationary features on graphs.
Institute for Pure and Applied Mathematics, UCLA
February 7, 2018
For more information: http://www.ipam.ucla.edu/programs/workshops/new-deep-learning-techniques/?tab=overview
Видео Xavier Bresson: "Convolutional Neural Networks on Graphs" канала Institute for Pure & Applied Mathematics (IPAM)
"Convolutional Neural Networks on Graphs"
Xavier Bresson, Nanyang Technological University, Singapore
Abstract: Convolutional neural networks have greatly improved state-of-the-art performances in computer vision and speech analysis tasks, due to its high ability to extract multiple levels of representations of data. In this talk, we are interested in generalizing convolutional neural networks from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, telecommunication networks, or words' embedding. We present a formulation of convolutional neural networks on graphs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs. Numerical experiments demonstrate the ability of the system to learn local stationary features on graphs.
Institute for Pure and Applied Mathematics, UCLA
February 7, 2018
For more information: http://www.ipam.ucla.edu/programs/workshops/new-deep-learning-techniques/?tab=overview
Видео Xavier Bresson: "Convolutional Neural Networks on Graphs" канала Institute for Pure & Applied Mathematics (IPAM)
Показать
Комментарии отсутствуют
Информация о видео
17 февраля 2018 г. 3:41:09
00:40:48
Другие видео канала
Graph neural networks: Variations and applications
Jure Leskovec: "Large-scale Graph Representation Learning"
But what is the Fourier Transform? A visual introduction.
1D Convolutional Neural Networks for Time Series Modeling - Nathan Janos, Jeff Roach
Intro to Relational - Graph Convolutional Networks
Tom Goldstein: "What do neural loss surfaces look like?"
Lecture 30 — The Graph Laplacian Matrix (Advanced) | Stanford University
An Introduction to Graph Neural Networks: Models and Applications
Lecture 31 — Examples of Eigendecompositions of Graphs (Advanced) | Stanford
Michael Bronstein - Geometric deep learning on graphs: going beyond Euclidean data
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Introduction to Capsules by Sara Sabour, Google
Graph Node Embedding Algorithms (Stanford - Fall 2019)
Graph Convolutional Neural Networks
Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs
Geometric Deep Learning on Graphs and Manifolds - #NIPS2017![[S+SSPR 2020] Graph Transformer: Learning Better Representations for Graph Neural Network](https://i.ytimg.com/vi/xS4bNwhbs6Q/default.jpg)
[S+SSPR 2020] Graph Transformer: Learning Better Representations for Graph Neural Network
Graph Convolutional Networks (GCNs) made simple
How convolutional neural networks work, in depth