Equivariant Neural Networks | Part 1/3 - Introduction

preview_player
Показать описание
▬▬ Papers / Resources ▬▬▬

▬▬ Used Music ▬▬▬▬▬▬▬▬▬▬▬
Music from #Uppbeat (free for Creators!):
License code: WXVHOOZRRWDUCKIU

▬▬ Used Icons ▬▬▬▬▬▬▬▬▬▬

▬▬ Timestamps ▬▬▬▬▬▬▬▬▬▬▬
00:00 Introduction
00:45 Equivariance and Invariance
03:03 CNNs are translation equivariant
04:00 Math notation
04:25 Visual intuition
05:08 Symmetries
06:22 Why are CNNs not rotation equivariant?
07:14 Inductive biases reduce the flexibility
08:10 What's wrong with data augmentations?
09:32 Motivations for Equivariant Neural Networks
09:55 You've unlocked a checkpoint.
10:07 Naturally occuring equivariance
10:50 Group Equivariant Convolutional Neural Networks
11:37 Group Theory (on a high level)
12:41 An example and the matrix notation
13:50 Group axioms
14:32 Cayley tables
15:33 Examples for groups
16:38 Applications of Equivariant Neural Networks
18:30 Final Checkpoint :)

▬▬ Support me if you like 🌟

▬▬ My equipment 💻
  1. DeepFindr
  2. Equivariant Deep Learning
  3. Group Convolution
  4. Group Convolutional Neural Networks
  5. SE(3)
  6. SO(3)
Рекомендации по теме
Equivariant Neural Networks 0:18:51

Equivariant Neural Networks | Part 1/3 - Introduction

Equivariant Neural Networks 0:15:57

Equivariant Neural Networks | Part 2/3 - Generalized CNNs

Equivariant Neural Networks 0:16:19

Equivariant Neural Networks | Part 3/3 - Transformers and GNNs

Equivariant Neural Networks 1:23:52

Equivariant Neural Networks (SGP Graduate School 2024)

Equivariant Neural Networks 0:53:28

Equivariant Neural Networks for Learning Spatiotemporal Dynamics, R.Walters, Northeastern University

A Complete Beginner's 1:46:06

A Complete Beginner's Guide To G-Invariant and G-Equivariant Neural Networks (02/08/2024) - Par...

Geometric Deep Learning, 0:06:55

Geometric Deep Learning, visualising a forward pass through an equivariant neural network

Group Equivariant Deep 0:18:43

Group Equivariant Deep Learning - Lecture 3.1: Motivation for SE(3) equivariant graph NNs

Clifford Group Equivariant 1:01:23

Clifford Group Equivariant Neural Networks | David Ruhe

Part 3: E(n) 0:11:24

Part 3: E(n) Equivariant Graph Neural Networks

Group Equivariant Deep 0:33:08

Group Equivariant Deep Learning - Lecture 3.2: Equivariant message passing as non-linear convolution

Equivariant Subgraph Aggregation 1:42:41

Equivariant Subgraph Aggregation Networks | Beatrice Bevilacqua, Fabrizio Frasca & Derek Lim

A Complete Beginner's 1:19:02

A Complete Beginner's Guide To G-Invariant and G-Equivariant Neural Networks (02/08/2024) - Par...

G-invariant Neural Networks 0:05:17

G-invariant Neural Networks (part 1)

E($3$) Equivariant Graph 0:10:27

E($3$) Equivariant Graph Neural Networks for Particle-Based Fluid Mechanics - ArXiv:2304

E(n) Equivariant Graph 1:11:25

E(n) Equivariant Graph Neural Networks - ECS 289G Talk

A Complete Beginner's 1:33:18

A Complete Beginner's Guide To G-Invariant and G-Equivariant Neural Networks (02/09/2024)

CNNs on Surfaces 0:19:47

CNNs on Surfaces using Rotation-equivariant Features

Enhancing interpretability of 0:05:00

Enhancing interpretability of equivariant neural networks... - Hao Xu - 3DSIG - Poster - ISMB 2022

E(3)-equivariant graph neural 0:00:22

E(3)-equivariant graph neural networks for data-efficient and accurate interatomic po... | RTCL.TV

Equivariant Machine Learning 1:12:15

Equivariant Machine Learning

Rotation Equivariant Deep 0:03:51

Rotation Equivariant Deep Neural Network (RED-NN)

Equivariant Networks and 0:36:23

Equivariant Networks and Natural Graph Networks - Taco Cohen

Group Equivariant Deep 0:20:46

Group Equivariant Deep Learning - Lecture 1.3: Regular group convolutional neural networks

Комментарии
Автор

Honestly this is one of the best introduction to the topic. A lot of the lectures directly dive / start with group theory and people without relevent background immediately loose interest seeing the mathematical concepts and axioms. This channel deserves more subs and views ❤❤

ajwadakil
Автор

You have a good ability to explain difficult subjects easily. There are tutorial videos for Geometric Deep Learning from Bronstein(who organized GDL tutorial school with Cohen, Burna etc) which includes this concept, but their tutorial needs more math background. Excellent.

sari
Автор

I love your content, and often come back to recall important concepts. Thank you very much, and I hope that soon I will be able to afford to buy you a coffee.

jangradkowski
Автор

i've been looking at this topic these days, super helpful to wrap my head around better!

Blueshockful
Автор

Wonderful video, the examples are incredibly intuitive.

spaceflame
Автор

hi, where the lower complexity of the network is stated as an advantage.. complex in what sense? my definition of complex network means there are more filters/neurons/weights to learn.. so how would equivariance reduce connections? those are fixed by our hand-crafted layer topology, no?

imolafodor
Автор

Clean as fuck. Thank you very much. Nice visuals nice explanations. Easy to follow

gapsongg
Автор

Nice video, could you please also create video of capsule networks, through caps-net you can also achieve equivariance in images.

shaz-z
Автор

Is it possible to share the slides as well?

chinmay.prabhakar