Geometric Deep Learning (Part 1)

preview_player
Показать описание

See Part 2 here:

Slides can be found on:

0:00 Introduction
4:00 5Gs of Geometric Deep Learning
9:10 Invariances in Deep Learning Architectures
17:07 Knowing symmetries = Generalization
39:58 Mathematical Definition of Symmetries
46:12 Definition of Mathematical Group
48:45 Group action
1:00:22 Equivariance vs Invariance
1:08:58 Clarification of Mathematical symbols
1:11:09 Caveat: Invariance/Equivariance should not be applied at all levels of the network
1:13:28 Convolution Neural Networks (Translational Invariance/Equivariance)
1:21:50 Role of Data Augmentation
1:30:22 Modelling other invariances into CNNs
1:40:18 Graph Neural Networks (Permutation Invariance/Equivariance)
1:49:52 Graphs can be permuted arbitrarily
1:56:22 Q&A on GNNs
  1. John Tan Chong Min
  2. geometric deep learning
  3. homeomorphism
  4. isomorphism
Рекомендации по теме
Geometric Deep Learning 0:32:45

Geometric Deep Learning - Part 1

Geometric Deep Learning 2:06:03

Geometric Deep Learning (Part 1)

ICLR 2021 Keynote 0:38:27

ICLR 2021 Keynote - 'Geometric Deep Learning: The Erlangen Programme of ML' - M Bronstein

GEOMETRIC DEEP LEARNING 3:33:23

GEOMETRIC DEEP LEARNING BLUEPRINT

Understanding Graph Neural 0:08:18

Understanding Graph Neural Networks | Part 1/3 - Introduction

Geometric Deep Learning 0:38:56

Geometric Deep Learning - Lab 1

Geometric Deep Learning 0:10:25

Geometric Deep Learning

Geometric Deep Learning 1:31:25

Geometric Deep Learning - Michael Bronstein - MLSS 2020, Tübingen

Foundations for Machine 0:36:05

Foundations for Machine Learning | Linear Algebra | Product of 2 matrices = Composite Transformation

Lecture 1: A 1:34:14

Lecture 1: A Brief History of Geometric Deep Learning - Michael Bronstein

AMMI Course 'Geometric 0:59:12

AMMI Course 'Geometric Deep Learning' - Lecture 1 (Introduction) - Michael Bronstein

Deep Learning: Graph 0:13:40

Deep Learning: Graph Deep Learning - Part 1

AMMI 2022 Course 1:14:59

AMMI 2022 Course 'Geometric Deep Learning' - Lecture 1 (Introduction) - Michael Bronstein

Geometric Deep Learning 0:58:16

Geometric Deep Learning for Drug Discovery

Geometric Deep Learning 0:45:30

Geometric Deep Learning | Michael Bronstein || Radcliffe Institute

Michael Bronstein - 1:23:00

Michael Bronstein - Geometric Deep Learning Pt.1

Geometric deep learning, 1:00:09

Geometric deep learning, from Euclid to drug design

Geometric Deep Learning 1:05:26

Geometric Deep Learning Part 1 | Third Nepal Winter School in AI | Day 8 (2021)

Tutorial on Geometric 1:33:07

Tutorial on Geometric Deep Learning - Part II

Geometric Deep Learning 0:55:49

Geometric Deep Learning - Michael M. Bronstein

Geometric Deep Learning 0:59:14

Geometric Deep Learning (Part 2)

Geometric Deep Learning 0:45:43

Geometric Deep Learning II: Georg Gottwald

Geometric Deep Learning 1:23:29

Geometric Deep Learning - Understanding DL 24

2021 2.2 Geometric 0:55:05

2021 2.2 Geometric Deep Learning Past, Present, And Future - Michael Bronstein

Комментарии
Автор

At 44:00, it is actually an automorphism, a subset of isomorphism.

For an isomorphism, you do not need to have the mapped output domain be equal to the range of the input, but in automorphism you must.

johntanchongmin